© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 8358
    Prev
    Next
    INDEX
    Explanations

    programming constructs or structure in code, especially related to class definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithEmail
    -0.60
    ształ
    -0.56
    AsStream
    -0.53
     Vole
    -0.52
     Ria
    -0.50
    minder
    -0.50
    Iconic
    -0.49
     mustard
    -0.48
    rün
    -0.47
    transform
    -0.47
    POSITIVE LOGITS
    expandindo
    1.19
    ViewFeatures
    0.89
    private
    0.75
    endregion
    0.74
    BASEPATH
    0.73
    addCriterion
    0.71
    <eos>
    0.70
     CURIAM
    0.70
     Audiodateien
    0.69
    public
    0.67
    Activations Density 0.014%

    No Known Activations