© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 2172
    Prev
    Next
    INDEX
    Explanations

    numeric data and values related to costs or estimates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $,
    -1.02
    $
    -1.02
    $-
    -1.01
    $}
    -1.00
    $}}
    -0.93
    $\\
    -0.93
    $.
    -0.91
    $;
    -0.90
    $=
    -0.89
    ${
    -0.87
    POSITIVE LOGITS
     MainAxisSize
    0.50
    setGeometry
    0.46
    parsedMessage
    0.42
    Filmographie
    0.41
    gonic
    0.40
    stateMutability
    0.40
     tinta
    0.40
    ArrowToggle
    0.39
    aarrggbb
    0.39
    Géographie
    0.39
    Activations Density 0.858%

    No Known Activations