© 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. 9905
    Prev
    Next
    INDEX
    Explanations

    patterns of whitespace and indentation in code or structured text

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

    C code snippets with "return 0" or "next_bio == NULL"

    np_acts-logits-general · gemini-2.0-flash

    return 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
    int
    -0.54
    ("")
    -0.52
     vett
    -0.52
    -0.50
    ++

    -0.49
     []

    -0.47
     gold
    -0.46
    ↵
    -0.46
    Gold
    -0.44
    ariConfig
    -0.43
    POSITIVE LOGITS
     autorytatywna
    0.82
    harapkan
    0.78
     nahilalakip
    0.77
     дописавши
    0.77
     consultato
    0.76
    fillType
    0.72
    saraba
    0.71
    Šaltiniai
    0.71
    versaire
    0.70
    queryInterface
    0.69
    Activations Density 0.020%
    No Known Activations