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. 81225
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the phrase "of the."

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

    top/bottom/back/center of

    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
    addCriterion
    -0.72
     nahilalakip
    -0.64
    TemporalType
    -0.59
     myſelf
    -0.59
    AppMethodBeat
    -0.59
     MainAxisSize
    -0.59
    InjectAttribute
    -0.59
    AddTagHelper
    -0.58
    findpost
    -0.58
    mobileqq
    -0.57
    POSITIVE LOGITS
    endOf
    0.62
    AtEndOf
    0.56
    EndOf
    0.56
    Inside
    0.45
     of
    0.45
    TopLeft
    0.43
    yl
    0.43
    OnTop
    0.43
    aman
    0.40
    pagin
    0.40
    Activations Density 0.025%

    No Known Activations