© 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. 7797
    Prev
    Next
    INDEX
    Explanations

    function calls and assignments in programming code

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

    Code that uses string splitting

    np_acts-logits-general · gemini-2.0-flash

    splitting strings

    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
     himo
    -0.46
    fread
    -0.44
    favorited
    -0.44
     evoked
    -0.42
    nsito
    -0.42
    setObjectName
    -0.40
    inheritdoc
    -0.38
     гро
    -0.38
     Mag
    -0.38
     look
    -0.37
    POSITIVE LOGITS
     split
    0.93
    split
    0.92
     Split
    0.86
    Split
    0.84
    replace
    0.82
     StringTokenizer
    0.82
    plit
    0.75
    MigrationBuilder
    0.75
     splitting
    0.75
     replace
    0.74
    Activations Density 0.097%

    No Known Activations