© 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. 9-GEMMASCOPE-RES-16K
    11. 10942
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives and actions related to grooming and maintenance

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

    Cutting hair or grass

    np_acts-logits-general · gemini-2.0-flash

    cutting, shearing, and grooming

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Settlements
    -0.46
     settlements
    -0.45
     ujednoznacz
    -0.44
     uParam
    -0.41
    ARROLL
    -0.41
    RefNanny
    -0.40
    settlement
    -0.39
    makeText
    -0.39
     menyel
    -0.39
    setValues
    -0.39
    POSITIVE LOGITS
     haircut
    0.75
     trimming
    0.69
     potong
    0.68
     shave
    0.66
     scissors
    0.63
     shaving
    0.63
    剪
    0.62
     shaved
    0.60
     cut
    0.60
     pruning
    0.59
    Activations Density 0.158%

    No Known Activations