© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 12049
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to handling, managing, or coping with situations or tasks

    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
     gql
    -0.74
    windowFixed
    -0.72
     smtplib
    -0.71
    헌
    -0.69
     تضيفلها
    -0.67
     ExecuteAsync
    -0.66
     surla
    -0.65
     perfeita
    -0.62
     pouvoit
    -0.62
    IntoConstraints
    -0.62
    POSITIVE LOGITS
     dealt
    0.95
     issues
    0.89
    Dealing
    0.85
     handles
    0.85
     handle
    0.84
     deal
    0.84
     Handles
    0.83
     Dealing
    0.79
     dealing
    0.79
     handling
    0.78
    Activations Density 0.187%

    No Known Activations