© 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-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105781
    Prev
    Next
    INDEX
    Explanations

    specific programming constructs and data structures in code

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

    Programming syntax elements, variable names, and container-related terminology in technical code and documentation contexts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ̓
    -0.41
     linkovi
    -0.38
    TypedDataSet
    -0.38
    Segoe
    -0.35
     inter
    -0.34
     word
    -0.33
     Mercier
    -0.32
     inch
    -0.31
    хождение
    -0.31
    Hentet
    -0.31
    POSITIVE LOGITS
     snippetHide
    0.71
    MigrationBuilder
    0.68
    +#+#
    0.52
    UrlResolution
    0.51
     Meksiku
    0.49
    makeConstraints
    0.49
    protoimpl
    0.47
     AssemblyCompany
    0.46
    ActionCreators
    0.46
    verwijspagina
    0.45
    Activations Density 0.151%

    No Known Activations