© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 174
    Prev
    Next
    INDEX
    Explanations

    programming constructs and syntax structures in code snippets

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

    Lines containing '#define' and 'M_' or 'V_'

    np_acts-logits-general · gemini-2.0-flash

    c/c++ #define statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikispecies
    -0.69
     ModelExpression
    -0.64
    mogat
    -0.61
    .³
    -0.59
     resourceCulture
    -0.58
     setAddress
    -0.56
     confronti
    -0.55
     doubtnut
    -0.55
     itſelf
    -0.55
    netje
    -0.55
    POSITIVE LOGITS
    DoubleQuotes
    0.74
     وتسجيلات
    0.57
    ‚¬
    0.56
    同上
    0.52
    (!__
    0.51
    Tembelea
    0.50
    </h2>
    0.49
    strictEqual
    0.48
    󠁢
    0.48
    （
    0.48
    Activations Density 0.617%

    No Known Activations