© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 5925
    Prev
    Next
    INDEX
    Explanations

    details related to scientific properties and characteristics of materials

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

    properties or characteristics of systems/materials and how they affect or determine functionality.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    technical or scientific nouns and terms that are central to the meaning of specialized academic content.

    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
     Reminders
    -0.35
     niech
    -0.34
    NotImplemented
    -0.34
     Reminder
    -0.33
    Rot
    -0.33
    utilisons
    -0.33
    hugs
    -0.32
    oredCriteria
    -0.32
    weł
    -0.31
    hobia
    -0.31
    POSITIVE LOGITS
     influence
    2.75
     influences
    2.41
    influence
    2.36
     Influence
    2.31
     influencing
    2.28
    影響
    2.23
    Influence
    2.23
     impact
    2.23
     affect
    2.20
     invloed
    2.16
    Activations Density 1.692%

    No Known Activations