© 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. 9-GEMMASCOPE-RES-131K
    11. 55641
    Prev
    Next
    INDEX
    Explanations

    instances of the word "clear" related to data or memory management functions

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

    clear/clearing/cleared

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Not in Any Lists

    No Comments

    Negative Logits
    PositiveButton
    -0.47
     onView
    -0.44
     Vikipedi
    -0.43
     jsonObj
    -0.43
     mundos
    -0.43
    BitmapFactory
    -0.40
    ându
    -0.40
    oni
    -0.39
    idey
    -0.38
    ymm
    -0.36
    POSITIVE LOGITS
    clear
    2.75
    Clear
    2.45
     Clear
    2.38
     clear
    2.25
    CLEAR
    2.03
     CLEAR
    1.96
     clears
    1.59
     cleared
    1.56
    cleared
    1.53
     Clears
    1.52
    Activations Density 0.003%

    No Known Activations