© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15303
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers used in programming or database management

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

    Code, often related to database or programming

    np_acts-logits-general · gemini-2.0-flash

    TCOOFF

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     ida
    -0.47
    rag
    -0.45
     follow
    -0.44
    guar
    -0.44
     sprend
    -0.41
     contrôle
    -0.41
     Follow
    -0.41
    bä
    -0.41
    DBG
    -0.41
     tailles
    -0.40
    POSITIVE LOGITS
    BeginContext
    0.92
    новништво
    0.85
    ChildScrollView
    0.82
    verwijspagina
    0.81
     Италијани
    0.78
     estekak
    0.77
     nahilalakip
    0.75
    GEBURTSDATUM
    0.74
    GTCX
    0.71
     AppColors
    0.70
    Activations Density 0.247%

    No Known Activations