© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 23340
    Prev
    Next
    INDEX
    Explanations

    characters and their interactions in narrative contexts

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

    proper names and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     autorytatywna
    -0.54
    homonymie
    -0.47
     geslacht
    -0.43
    Smarty
    -0.41
    ClassNotFound
    -0.40
     nghiệp
    -0.39
     icke
    -0.39
     peuple
    -0.38
    TemporalType
    -0.38
    plata
    -0.38
    POSITIVE LOGITS
    Chham
    0.58
    dflare
    0.43
     personally
    0.42
     tell
    0.41
     force
    0.38
    expandindo
    0.38
     teach
    0.37
    contentLoaded
    0.36
    ьаж
    0.36
     telling
    0.36
    Activations Density 0.041%

    No Known Activations