© 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. 4867
    Prev
    Next
    INDEX
    Explanations

    CSS property definitions and layout attributes

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

    CSS property names and their associated colon separators in stylesheets and style attributes.

    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
    omeness
    -0.27
     yyj
    -0.26
     doigt
    -0.25
     depth
    -0.25
    rowCount
    -0.23
     pattern
    -0.23
     nalazi
    -0.23
    angliski
    -0.23
    hilangan
    -0.23
    axaca
    -0.23
    POSITIVE LOGITS
    centers
    0.79
    center
    0.78
     center
    0.77
     TextAlign
    0.73
    Center
    0.73
     centers
    0.73
    AxisAlignment
    0.71
    CENTER
    0.71
     CENTER
    0.70
    centre
    0.68
    Activations Density 0.137%

    No Known Activations