© 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. 20-GEMMASCOPE-RES-16K
    11. 13035
    Prev
    Next
    INDEX
    Explanations

    lines of code with constructor or initialization methods

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

    Beginning of function or class definitions

    np_acts-logits-general · gemini-2.0-flash

    initialization code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.77
    MigrationBuilder
    -0.76
     typelib
    -0.70
     <=",
    -0.69
    LookAnd
    -0.68
    SourceChecksum
    -0.68
    jalá
    -0.67
    oulli
    -0.66
    ThroughAttribute
    -0.64
    EndGlobalSection
    -0.63
    POSITIVE LOGITS
    ArgsConstructor
    0.57
    INIT
    0.56
    Intial
    0.56
    initialValue
    0.56
     initWith
    0.52
     parents
    0.51
     maître
    0.51
     nargin
    0.51
     initial
    0.50
     init
    0.50
    Activations Density 0.134%

    No Known Activations