© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2299
    Prev
    Next
    INDEX
    Explanations

    specific programming constructs or patterns in code snippets

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

    code-related syntax and method calls, particularly in programming languages like Java, Go, or TypeScript.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     propOrder
    -1.16
    évaluateur
    -0.69
    archiviato
    -0.69
    PerformLayout
    -0.69
    RuleContext
    -0.67
    IsMutable
    -0.64
    writeFieldEnd
    -0.61
    StoryboardSegue
    -0.60
    SharedDtor
    -0.60
    viewDidLoad
    -0.59
    POSITIVE LOGITS
    __*/
    0.54
     the
    0.43
     an
    0.41
     a
    0.38
    <>(
    0.36
     either
    0.35
    TokenNameLPAREN
    0.35
    (
    0.34
     their
    0.34
    (\
    0.34
    Activations Density 0.108%

    No Known Activations