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. 20-GEMMASCOPE-RES-131K
    6. 75057
    Prev
    Next
    INDEX
    Explanations

    general references to facilities and the presence of various subjects or themes

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

    as with

    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
    Географиясе
    -0.69
     resourceCulture
    -0.68
    styleType
    -0.62
    ArgsConstructor
    -0.59
    awtextra
    -0.56
    SharedDtor
    -0.56
    ✨:
    -0.54
    setVerticalGroup
    -0.54
     Numerade
    -0.53
    GOTREF
    -0.53
    POSITIVE LOGITS
     sh
    0.37
    付
    0.37
    iello
    0.36
    sh
    0.35
    GEBURTSDATUM
    0.34
    case
    0.33
    wide
    0.33
    ide
    0.33
    Panel
    0.32
    eo
    0.32
    Activations Density 0.022%

    No Known Activations