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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 94943
    Prev
    Next
    INDEX
    Explanations

    HTML tags and attributes related to data binding and list views in web development

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

    list and grid views

    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
     propOrder
    -0.69
    UnusedPrivate
    -0.68
    complexContent
    -0.67
    findpost
    -0.60
    LookAnd
    -0.59
    ValueStyle
    -0.59
    DockStyle
    -0.59
    GEBURTS
    -0.53
    featureID
    -0.51
    MigrationBuilder
    -0.51
    POSITIVE LOGITS
    opsis
    0.37
     habet
    0.34
    zien
    0.34
    igert
    0.33
    ffichage
    0.33
    iglia
    0.33
    rufe
    0.33
     mostrarán
    0.32
     couverts
    0.32
    nser
    0.32
    Activations Density 0.003%

    No Known Activations