© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8352
    Prev
    Next
    INDEX
    Explanations

    references to code structure and functionality in programming

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

    Code snippets or specific field names

    np_acts-logits-general · gemini-2.0-flash

    data manipulation and programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    dis
    -0.45
     Upper
    -0.44
    光
    -0.44
    坎
    -0.44
     Asia
    -0.43
     dientes
    -0.42
    ab
    -0.42
    au
    -0.41
    AB
    -0.41
    재
    -0.40
    POSITIVE LOGITS
     الرياضيه
    1.10
    principalColumn
    1.03
    styleType
    1.02
    Искәрмәләр
    0.95
     calendriers
    0.91
    expandindo
    0.91
    parsedMessage
    0.90
    TintMode
    0.90
    IntoConstraints
    0.88
    bootstrapcdn
    0.88
    Activations Density 0.152%

    No Known Activations