© 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. 9-GEMMASCOPE-RES-16K
    11. 7262
    Prev
    Next
    INDEX
    Explanations

    keywords related to sales, discounts, and minification in programming tasks

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

    Code optimization and simplification

    np_acts-logits-general · gemini-2.0-flash

    mini and simplify

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.63
    parsedMessage
    -0.55
    ReusableCell
    -0.54
    ScopeManager
    -0.52
    èdia
    -0.46
    HostException
    -0.46
    zzleHttp
    -0.44
    LookAnd
    -0.44
    GeoNames
    -0.43
     onAnimation
    -0.43
    POSITIVE LOGITS
    minify
    0.47
    uglify
    0.45
     simpli
    0.44
     simplification
    0.43
     NDEBUG
    0.43
     optimization
    0.42
     cheap
    0.41
     economy
    0.40
     reduced
    0.39
     discount
    0.39
    Activations Density 0.494%

    No Known Activations