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. 20-GEMMASCOPE-RES-16K
    6. 1460
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical measurements, particularly related to variations and standard deviations

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

    Values with standard deviation

    np_acts-logits-general · gemini-2.0-flash

    mean ± standard deviation

    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
    principalTable
    -0.55
     autorytatywna
    -0.49
    ref
    -0.49
    .*")]
    -0.45
    SuspendLayout
    -0.43
    Hentet
    -0.43
     ref
    -0.43
     بيها
    -0.42
    يكب
    -0.42
     au
    -0.41
    POSITIVE LOGITS
     myſelf
    0.82
    ]='\
    0.82
    InSection
    0.77
     itſelf
    0.77
    CloseOperation
    0.76
    IntoConstraints
    0.71
     houſe
    0.70
     uſed
    0.69
     (±
    0.68
     himſelf
    0.67
    Activations Density 0.508%

    No Known Activations