© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 12938
    Prev
    Next
    INDEX
    Explanations

    references to time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.78
    batore
    -0.78
    🏻
    -0.77
    ']?>
    -0.76
     للمعارف
    -0.74
    >')
    -0.73
    /');
    -0.71
    corrhi
    -0.70
    IntoConstraints
    -0.69
    ="#">
    -0.69
    POSITIVE LOGITS
     periods
    1.42
     Periods
    1.32
     Period
    1.25
     period
    1.23
    PERIOD
    1.19
    Periods
    1.19
     PERIOD
    1.19
    periods
    1.16
    period
    1.15
    Period
    1.11
    Activations Density 0.126%

    No Known Activations