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. 11-GEMMASCOPE-RES-16K
    6. 13835
    Prev
    Next
    INDEX
    Explanations

    quantitative data and statistics related to population and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.73
    endphp
    -0.64
    tvguidetime
    -0.61
     hindurch
    -0.55
    หน่อย
    -0.52
    TCR
    -0.49
     indépendant
    -0.48
    archiviato
    -0.46
    randn
    -0.46
    честву
    -0.46
    POSITIVE LOGITS
    featureID
    0.69
    AndEndTag
    0.69
    帖最后由
    0.61
     <>",
    0.61
    EndInit
    0.59
    Alike
    0.59
    kloped
    0.59
    EndProject
    0.58
     Catawiki
    0.57
    ArgumentParser
    0.56
    Activations Density 0.457%

    No Known Activations