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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 3246
    Prev
    Next
    INDEX
    Explanations

    programming constructs and structural definitions in code

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

    Follows "Error" or "Code"

    np_acts-logits-general · gemini-2.0-flash

    Error Code, micro machines, small caps, Niche Jobs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lèvres
    -0.99
     leçons
    -0.93
     négociations
    -0.92
     épaules
    -0.91
     vœux
    -0.91
     vérit
    -0.85
     prisonniers
    -0.85
     prochaines
    -0.84
     renseignements
    -0.82
     navires
    -0.82
    POSITIVE LOGITS
     sands
    0.56
    kins
    0.55
    rics
    0.55
     coffees
    0.55
     heights
    0.55
     referenties
    0.54
     dbs
    0.54
     DMs
    0.54
     limes
    0.54
    ToBounds
    0.54
    Activations Density 0.942%

    No Known Activations