Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 64863
    Prev
    Next
    INDEX
    Explanations

    instances of the word "skip" in various contexts

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

    skip

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     
    -0.47
     .
    -0.43
     A
    -0.41
    .
    -0.40
    <strong>
    -0.38
     The
    -0.37
     arbet
    -0.37
     negócio
    -0.36
     overeen
    -0.36
     a
    -0.36
    POSITIVE LOGITS
     skip
    1.23
     skipped
    1.20
     skipping
    1.17
    skip
    1.16
     Skip
    1.14
     skips
    1.13
    Skip
    1.12
     SKIP
    1.11
    SKIP
    1.04
    skipped
    0.99
    Activations Density 0.007%

    No Known Activations