© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105593
    Prev
    Next
    INDEX
    Explanations

    HTML or layout related tags and structure

    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
     NBA
    -0.42
    AllowUser
    -0.39
    nbt
    -0.39
     he
    -0.37
    nofollow
    -0.36
    年
    -0.36
    TAWA
    -0.36
    openqa
    -0.35
     supp
    -0.35
    NBA
    -0.34
    POSITIVE LOGITS
    MigrationBuilder
    0.73
    BagConstraints
    0.70
    IntoConstraints
    0.69
    BagLayout
    0.67
    awtextra
    0.67
    SequentialGroup
    0.66
    LayoutPanel
    0.59
    sidemargin
    0.58
    aarrggbb
    0.57
     transfieras
    0.55
    Activations Density 0.006%

    No Known Activations