© 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. 12777
    Prev
    Next
    INDEX
    Explanations

    programming-related terminology and functions, particularly those pertaining to the JavaScript runtime and JIT (Just-In-Time) compilation processes

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

    Code snippets with "JIT" or "eval"

    np_acts-logits-general · gemini-2.0-flash

    evaluating code or expressions

    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
    ="@+
    -0.52
     Enid
    -0.42
     نکن
    -0.41
     Gaff
    -0.39
    osse
    -0.39
    ทย
    -0.39
    geom
    -0.39
    ility
    -0.38
    annt
    -0.38
     Splitter
    -0.38
    POSITIVE LOGITS
     EVAL
    0.70
     Eval
    0.69
    دانشنامهٔ
    0.66
     Evaluation
    0.66
    EVAL
    0.66
    évaluation
    0.66
    Evaluation
    0.65
     evaluation
    0.65
     Evaluations
    0.64
     eval
    0.64
    Activations Density 0.510%

    No Known Activations