© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 8500
    Prev
    Next
    INDEX
    Explanations

    phrases related to health impacts and benefits of various treatments and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to health benefits and medical research.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    phrases describing positive health or beneficial outcomes from treatments or interventions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    Language discussing the advantages or positive outcomes of something, particularly in health, policy, or program contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    statements about benefits or positive outcomes—often health-related—resulting from actions, interventions, activities, or policies.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -0.47
    EndContext
    -0.47
    MetaObject
    -0.43
    msgTypes
    -0.42
     &___
    -0.42
    :✨
    -0.41
    valget
    -0.37
    verifyException
    -0.37
    FDRE
    -0.36
     Shaffer
    -0.36
    POSITIVE LOGITS
     benefits
    2.72
    benefits
    2.36
     Benefits
    2.23
    Benefits
    2.20
     benefit
    2.19
     BENEFITS
    2.08
    BENEFITS
    1.97
    benefit
    1.96
     beneficios
    1.88
    Benefit
    1.86
    Activations Density 0.565%

    No Known Activations