© 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. 13511
    Prev
    Next
    INDEX
    Explanations

    summaries of outcomes or consequences connected to various actions or situations

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

    causal relationships expressed through "as a result of" constructions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
     danger
    -0.50
     possibility
    -0.49
     achievable
    -0.46
    threatening
    -0.45
     Likelihood
    -0.43
     attainable
    -0.43
     ✭✭
    -0.43
     importance
    -0.43
     important
    -0.42
     Risk
    -0.42
    POSITIVE LOGITS
     interactions
    0.66
     carelessness
    0.64
     actions
    0.62
     Handlungen
    0.61
    การ
    0.58
     efforts
    0.58
     działania
    0.58
     mismanagement
    0.58
     esforço
    0.58
     exposure
    0.57
    Activations Density 0.984%

    No Known Activations