© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 8858
    Prev
    Next
    INDEX
    Explanations

    quantitative data related to financial metrics and statistics

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

    Numerical values or quantities

    np_acts-logits-general · gemini-2.0-flash

    quantities and comparisons

    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
    Inner
    -0.56
     nahilalakip
    -0.54
    ⓧ
    -0.54
     Outer
    -0.50
    ScopeManager
    -0.49
    adaptiveStyles
    -0.48
    Outer
    -0.48
     Inner
    -0.47
    ahashi
    -0.47
    endtime
    -0.46
    POSITIVE LOGITS
     fewer
    1.20
     more
    1.17
     extra
    1.14
     less
    1.11
     supplémentaire
    0.94
     additional
    0.92
     aggiun
    0.91
     supplémentaires
    0.89
     więcej
    0.89
     tambahan
    0.89
    Activations Density 0.281%

    No Known Activations