© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1665
    Prev
    Next
    INDEX
    Explanations

    code syntax related to function definitions and error handling

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

    Code-related terms and symbols

    np_acts-logits-general · gemini-2.0-flash

    code keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     صوتيه
    -0.56
     فريبيس
    -0.56
    thâu
    -0.55
    WebVitals
    -0.53
     nahilalakip
    -0.50
    Datuak
    -0.49
    égique
    -0.48
     שוליים
    -0.48
    Controllo
    -0.47
     мәкал
    -0.47
    POSITIVE LOGITS
    AutoresizingMask
    0.38
    wantErr
    0.38
     dig
    0.36
    TileEntity
    0.35
    Szer
    0.34
    JsonIgnore
    0.33
    Mapping
    0.33
    ActionCreators
    0.32
    CGRect
    0.32
     Sorte
    0.32
    Activations Density 0.245%

    No Known Activations