Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2242
    Prev
    Next
    INDEX
    Explanations

    structured programming elements and method definitions in code

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

    Code-related symbols and parentheses

    np_acts-logits-general · gemini-2.0-flash

    legal, code, and scientific text

    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
    اقرأ
    -0.63
     Majefty
    -0.62
    wiſe
    -0.62
     ModelExpression
    -0.62
     RIPRODUZIONE
    -0.61
    enumi
    -0.61
    Personendaten
    -0.60
    Portály
    -0.60
    ".
    
    -0.59
    Demikian
    -0.59
    POSITIVE LOGITS
    expandindo
    0.84
    enderror
    0.65
    rungsseite
    0.57
     виправивши
    0.55
    uxxxx
    0.53
    でしたか
    0.51
     crossorigin
    0.50
     gepubliceerd
    0.49
     CURIAM
    0.49
    unknownFields
    0.47
    Activations Density 0.115%

    No Known Activations