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. 15-GEMMASCOPE-RES-16K
    6. 12735
    Prev
    Next
    INDEX
    Explanations

    specific mathematical symbols and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oherty
    -0.64
     Baillargeon
    -0.61
    Становништво
    -0.60
    IVEREF
    -0.59
    RenderAtEndOf
    -0.56
    RectangleBorder
    -0.56
    Datuak
    -0.56
     dignité
    -0.56
     برانيه
    -0.56
    RegressionTest
    -0.55
    POSITIVE LOGITS
     regularly
    0.73
     daily
    0.69
     weekly
    0.62
     Regularly
    0.61
     دائ
    0.55
     consistently
    0.55
    daily
    0.54
     periodic
    0.54
     regular
    0.53
     nightly
    0.53
    Activations Density 0.775%

    No Known Activations