© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 37905
    Prev
    Next
    INDEX
    Explanations

    terms related to genetics and genomic concepts

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

    connectors preceding descriptions

    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
    ients
    -0.47
    :✨
    -0.44
    nad
    -0.44
    nodoc
    -0.43
     poveznice
    -0.43
    katan
    -0.40
    Segoe
    -0.40
    iod
    -0.40
     препратки
    -0.40
    formats
    -0.40
    POSITIVE LOGITS
    expandindo
    0.53
     leſs
    0.42
     <>",
    0.41
     getIs
    0.40
     '{@
    0.40
     gambe
    0.38
    MigrationBuilder
    0.38
    MemoryWarning
    0.37
     similar
    0.37
    astéroïdes
    0.36
    Activations Density 0.078%

    No Known Activations