© 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. 21-GEMMASCOPE-RES-16K
    11. 2167
    Prev
    Next
    INDEX
    Explanations

    code structure and definitions related to programming constructs like classes and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.83
    DoubleQuotes
    -0.79
    featureID
    -0.75
     للمعارف
    -0.71
    日閲覧
    -0.65
    addCriterion
    -0.64
    migrationBuilder
    -0.64
    crollView
    -0.59
    دانشنامهٔ
    -0.59
    ArrowToggle
    -0.59
    POSITIVE LOGITS
     func
    0.90
    func
    0.87
     var
    0.80
    override
    0.79
     createSlice
    0.68
    var
    0.68
     let
    0.67
     init
    0.62
    struct
    0.57
    convenience
    0.57
    Activations Density 0.146%

    No Known Activations