© 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. 10058
    Prev
    Next
    INDEX
    Explanations

    instances of instructions encouraging user interaction or engagement

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

    clickable call-to-action phrases that direct users to access additional content or information.

    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
    vera
    -0.38
    Географија
    -0.35
    vere
    -0.33
    complexContent
    -0.33
    TypedDataSet
    -0.33
     JsonConvert
    -0.32
    zulegen
    -0.32
     Verhalten
    -0.32
     userDao
    -0.32
    SequentialGroup
    -0.32
    POSITIVE LOGITS
     click
    0.77
     Click
    0.77
    CLICK
    0.71
     clicks
    0.69
     CLICK
    0.68
    click
    0.63
     nakalista
    0.63
     Klick
    0.61
    clicked
    0.61
     clicked
    0.61
    Activations Density 0.075%

    No Known Activations