© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104548
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to body measurements and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    \{\\
    -0.59
    ChildScrollView
    -0.56
     oprot
    -0.51
    󠁢
    -0.51
    jiny
    -0.50
    CppCodeGen
    -0.49
    tonic
    -0.49
    }{*}{}
    -0.48
     arb
    -0.47
     Redu
    -0.47
    POSITIVE LOGITS
     comuniques
    0.38
     Connectez
    0.36
     médicale
    0.35
     AssemblyCompany
    0.35
     bleib
    0.34
     Inscrivez
    0.34
    setVerticalGroup
    0.34
     ücret
    0.33
    addGroup
    0.32
     econômica
    0.32
    Activations Density 0.026%

    No Known Activations