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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73458
    Prev
    Next
    INDEX
    Explanations

    terms related to comics and comic strips

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    cestry
    -0.58
    BindView
    -0.56
    lavia
    -0.51
     VIII
    -0.50
     NLA
    -0.50
    itudinal
    -0.48
    esthesia
    -0.47
    emplo
    -0.47
     Lana
    -0.47
     ditetapkan
    -0.46
    POSITIVE LOGITS
    Comic
    1.01
     comics
    1.01
     comic
    0.94
     Comic
    0.93
     Comics
    0.90
    Comics
    0.86
    comic
    0.79
    comics
    0.63
     cómics
    0.54
     漫画
    0.51
    Activations Density 0.004%

    No Known Activations