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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 124553
    Prev
    Next
    INDEX
    Explanations

    attributes and properties related to HTML or form elements

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

    colorectal cancer or layout dimensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    afficheront
    -0.38
    gemä
    -0.34
    alertDialog
    -0.34
    凈
    -0.34
    __/
    -0.34
    $($
    -0.33
     (;;
    -0.33
    ️⃣
    -0.33
    ]")]
    -0.33
    Kaieteur
    -0.33
    POSITIVE LOGITS
    cols
    2.81
     cols
    2.52
    Cols
    1.81
    COLS
    1.48
     Columns
    1.19
     columns
    1.04
    COLUMNS
    1.02
     Rows
    0.97
    Columns
    0.97
    rows
    0.97
    Activations Density 0.003%

    No Known Activations