© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4227
    Prev
    Next
    INDEX
    Explanations

    elements of programming syntax and structure in code snippets

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

    Code snippets in C++ or Java

    np_acts-logits-general · gemini-2.0-flash

    public method and class declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    AddTagHelper
    -0.54
    Viitteet
    -0.47
     onOptions
    -0.46
    addCriterion
    -0.45
     Begründung
    -0.43
    WriteTagHelper
    -0.43
    DIPSETTING
    -0.43
    :✨
    -0.43
    atouille
    -0.42
     gewünschten
    -0.41
    POSITIVE LOGITS
    ScopeManager
    0.44
    SourceChecksum
    0.43
    endmodule
    0.39
    mapStateToProps
    0.39
    
    0.37
    obus
    0.37
    setVerticalGroup
    0.36
     AUX
    0.35
     MDR
    0.35
    styleable
    0.35
    Activations Density 0.172%

    No Known Activations