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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-131K
    6. 7480
    Prev
    Next
    INDEX
    Explanations

    references to monetary amounts or financial figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    i
    -0.47
    ii
    -0.39
    ee
    -0.38
    iii
    -0.37
    :
    -0.36
     observed
    -0.34
     care
    -0.32
     συνε
    -0.32
    bauen
    -0.32
    ,
    -0.32
    POSITIVE LOGITS
     $\$
    1.05
    {\$
    1.00
    dollar
    0.97
     $_(
    0.94
    dollars
    0.92
     \$
    0.92
     DOLLARS
    0.89
    $\$
    0.87
     Monfieur
    0.87
    ﹧
    0.85
    Activations Density 0.030%

    No Known Activations