© 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. 22-GEMMASCOPE-RES-16K
    11. 3157
    Prev
    Next
    INDEX
    Explanations

    function definitions and method signatures in programming code

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

    Go programming language errors

    np_acts-logits-general · gemini-2.0-flash

    returning error

    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
     devront
    -0.61
    NOPQRST
    -0.56
     Turing
    -0.50
     suffit
    -0.48
     devra
    -0.47
     pourront
    -0.47
     Zeich
    -0.47
    ことは
    -0.45
    UVWXYZ
    -0.45
    ことが
    -0.45
    POSITIVE LOGITS
     interface
    0.86
     []
    0.81
    interface
    0.81
     bool
    0.79
    [][]
    0.73
    bool
    0.72
     map
    0.72
    []
    0.68
     error
    0.67
    IntoConstraints
    0.65
    Activations Density 0.113%

    No Known Activations