© 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. 23591
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "wind up" along with related contexts of concluding or wrapping things up

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

    winding and winding down

    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
    ⓧ
    -0.53
    //(
    -0.50
    webElementXpaths
    -0.47
    antMatchers
    -0.43
     bricolaje
    -0.42
     krij
    -0.41
     Samo
    -0.41
    ğraf
    -0.41
    Hugs
    -0.40
    })->
    -0.40
    POSITIVE LOGITS
     winding
    0.56
     wound
    0.53
    ChildScrollView
    0.52
    __':
    0.50
     Winding
    0.48
    PerformLayout
    0.47
    wound
    0.46
    Wound
    0.46
     onCancelled
    0.45
     onAnimation
    0.45
    Activations Density 0.002%

    No Known Activations