© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 13271
    Prev
    Next
    INDEX
    Explanations

    instances of the word "skip" and its variations, indicating instructions or suggestions to bypass or omit sections within a context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    "Skip" or skipping actions

    np_acts-logits-general · gemini-2.0-flash

    skip

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Rptr
    -0.35
     repente
    -0.34
    SerializeField
    -0.32
    IsTrue
    -0.32
     sembler
    -0.31
    URLException
    -0.30
     investigador
    -0.30
     react
    -0.30
    bigcap
    -0.29
     cat
    -0.29
    POSITIVE LOGITS
     skip
    1.67
     skipped
    1.60
     Skip
    1.59
     skipping
    1.55
    skip
    1.55
    Skip
    1.52
     skips
    1.46
     SKIP
    1.42
    SKIP
    1.32
    skipped
    1.27
    Activations Density 0.420%

    No Known Activations