© 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. 104760
    Prev
    Next
    INDEX
    Explanations

    references to scientific instruments and data analysis methods

    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
     ProtoMessage
    -0.73
     invokingState
    -0.72
    tagHelperRunner
    -0.70
    
    -0.69
     tartalomajánló
    -0.68
     चीज़ों
    -0.65
    homonymie
    -0.64
     ब्रेकडाउन
    -0.63
    verifyException
    -0.62
     مشين
    -0.61
    POSITIVE LOGITS
    før
    0.33
    止ま
    0.33
     rapports
    0.32
    cartão
    0.32
     manuals
    0.32
     étu
    0.32
    camos
    0.32
     cruda
    0.32
    çoivent
    0.32
    ®.
    0.32
    Activations Density 0.147%

    No Known Activations