© 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. 5394
    Prev
    Next
    INDEX
    Explanations

    parentheses and their usage within the text

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

    Code-related punctuation and symbols

    np_acts-logits-general · gemini-2.0-flash

    known substitution

    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
    Personensuche
    -0.76
    AddTagHelper
    -0.72
     onAnimation
    -0.69
    webElementGuid
    -0.68
    providedIn
    -0.67
    rungsseite
    -0.67
    expandindo
    -0.67
    .*")]
    -0.67
     onCancelled
    -0.67
     مرئيه
    -0.64
    POSITIVE LOGITS
     =>
    0.72
    =>
    0.64
     async
    0.59
    PMailer
    0.55
    async
    0.54
     =>
    0.47
     faster
    0.47
     rangs
    0.46
    typeorm
    0.45
    LocalStorage
    0.44
    Activations Density 0.042%

    No Known Activations