Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 9300
    Prev
    Next
    INDEX
    Explanations

    import statements in JavaScript

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

    import statements in code.

    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
    -------------</
    -0.65
    writeFieldEnd
    -0.59
     InputDecoration
    -0.58
    ViewImports
    -0.56
    IntoConstraints
    -0.53
    transQ
    -0.50
    ModelAdmin
    -0.49
    }>;
    -0.48
     kaarangay
    -0.47
    AnchorTagHelper
    -0.46
    POSITIVE LOGITS
     '
    0.58
     '@
    0.52
     ‘
    0.50
     autorytatywna
    0.49
     "
    0.46
    SuppressLint
    0.43
     “
    0.42
     androidx
    0.38
    hetics
    0.38
     "@
    0.37
    Activations Density 0.048%

    No Known Activations