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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23-GEMMASCOPE-RES-16K
    6. 11320
    Prev
    Next
    INDEX
    Explanations

    terms related to quality and comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ьаж
    -0.53
    Married
    -0.53
     najbol
    -0.53
     normality
    -0.53
    ленность
    -0.52
     onlyOwner
    -0.52
     ModelExpression
    -0.51
     ύ
    -0.50
     sconfit
    -0.49
     seriousness
    -0.49
    POSITIVE LOGITS
     ویکی‌پدیای
    0.68
     versa
    0.67
     inviting
    0.65
    клопе
    0.56
    thyst
    0.56
    styleable
    0.56
    laught
    0.56
     versi
    0.55
    ContentLoaded
    0.55
     satisfying
    0.54
    Activations Density 0.188%

    No Known Activations