© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 96501
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "sky" and its variations

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

    sky followed by names, places, or concepts

    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
    ment
    -0.51
    ments
    -0.48
    ization
    -0.39
    tų
    -0.38
     part
    -0.38
     delen
    -0.38
     portion
    -0.38
    moin
    -0.37
     Cohn
    -0.37
     "
    -0.36
    POSITIVE LOGITS
    Sky
    1.41
     Sky
    1.36
     SKY
    1.34
     sky
    1.13
    SKY
    1.09
     Skywalker
    0.94
     Skyline
    0.91
     skys
    0.90
    sky
    0.90
     pleaſure
    0.88
    Activations Density 0.016%

    No Known Activations