© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 72596
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'first' and related concepts

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

    first occurrence or item

    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
     the
    -0.53
     Tatsache
    -0.52
    Personensuche
    -0.51
     cuestión
    -0.51
    atorics
    -0.49
     Dingen
    -0.44
     that
    -0.44
     questões
    -0.44
    vább
    -0.44
     everyone
    -0.44
    POSITIVE LOGITS
     own
    0.67
    ⤹
    0.52
     GoogleFonts
    0.50
     favorite
    0.49
    His
    0.49
    My
    0.48
    WireFormatLite
    0.48
    Exper
    0.47
     preferred
    0.47
     favourite
    0.45
    Activations Density 0.019%

    No Known Activations