© 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. 5226
    Prev
    Next
    INDEX
    Explanations

    code statements and declarations within a programming context

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

    code-related tokens and programming syntax (like 'const', '=', variables, function parameters).

    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
     ujednoznacz
    -0.53
    Rhestr
    -0.49
    contentLoaded
    -0.49
    Filmografia
    -0.47
    oredCriteria
    -0.44
    ientôt
    -0.42
     iParam
    -0.42
    omiast
    -0.41
    makeConstraints
    -0.41
    wahl
    -0.41
    POSITIVE LOGITS
    AnchorStyles
    0.45
    AndroidJUnit
    0.40
    ScopeManager
    0.38
     للاسماء
    0.38
    scenarios
    0.38
     Twice
    0.38
     Plan
    0.37
    План
    0.37
    солю
    0.37
     architect
    0.37
    Activations Density 0.085%

    No Known Activations