© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 9852
    Prev
    Next
    INDEX
    Explanations

    specific variable names or attributes related to graphics or positioning in programming

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

    coordinate variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    :],
    -0.35
    <blockquote>
    -0.33
    """
    -0.32
     gesteld
    -0.31
     medieval
    -0.31
    Dud
    -0.31
    import
    -0.31
     spot
    -0.30
    quot
    -0.30
    popover
    -0.29
    POSITIVE LOGITS
    IntoConstraints
    0.81
    transQ
    0.68
    Хьажоргаш
    0.61
    DotNetBar
    0.59
    setVerticalGroup
    0.54
     sánchez
    0.54
    gonic
    0.53
     barbati
    0.52
     crochê
    0.52
     TextInputType
    0.52
    Activations Density 0.013%

    No Known Activations