© 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. 8197
    Prev
    Next
    INDEX
    Explanations

    information related to discussions or conversations among individuals

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

    periods and punctuation marks that end sentences or major sections in text.

    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
     surla
    -0.44
    glLoadIdentity
    -0.39
    abestanden
    -0.39
    ddots
    -0.39
    WriteLiteral
    -0.39
    PreExecute
    -0.38
     Xinhua
    -0.37
     وتسجيلات
    -0.37
    tagHelperRunner
    -0.36
    ArrowToggle
    -0.36
    POSITIVE LOGITS
     listeners
    1.16
     listener
    1.09
     episode
    0.89
     Episode
    0.84
     Listener
    0.83
    Episode
    0.83
     Listen
    0.82
     listen
    0.78
    episode
    0.78
     listening
    0.75
    Activations Density 0.119%

    No Known Activations