© 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. 12400
    Prev
    Next
    INDEX
    Explanations

    references to lips or lip-related terms

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

    lips

    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
     Central
    -0.54
     CKD
    -0.50
     Que
    -0.49
     للمعارف
    -0.48
     Catar
    -0.47
     Carri
    -0.46
     System
    -0.46
     North
    -0.46
     Eas
    -0.46
    PDOException
    -0.45
    POSITIVE LOGITS
     lips
    1.13
     lèvres
    1.09
     Lips
    1.07
     lip
    1.06
    Lip
    1.04
     labios
    1.02
    Lips
    0.99
     Lip
    0.96
     bibir
    0.82
     LIP
    0.82
    Activations Density 0.002%

    No Known Activations