© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 469
    Prev
    Next
    INDEX
    Explanations

    references to food and web-related terms

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

    Followed by "at", "to", or "has"

    np_acts-logits-general · gemini-2.0-flash

    size of buckles

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    間
    -0.43
     large
    -0.40
    setcounter
    -0.39
     Ge
    -0.39
     hefty
    -0.39
    prime
    -0.39
    ↵↵
    -0.38
     heavy
    -0.38
     the
    -0.38
     கி
    -0.38
    POSITIVE LOGITS
     getItemId
    0.64
    AndEndTag
    0.63
     CURIAM
    0.63
     pinulongan
    0.60
     nonUne
    0.57
     Wikimedijinoj
    0.57
    isContained
    0.56
     MenuView
    0.53
    AccessorTable
    0.51
    tomans
    0.51
    Activations Density 0.012%

    No Known Activations