© 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. 104618
    Prev
    Next
    INDEX
    Explanations

    terms related to variety and compatibility of products or technologies

    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
    ResponseStatus
    -0.31
     aikana
    -0.31
    ulisan
    -0.29
    identiality
    -0.28
     lack
    -0.28
    бие
    -0.27
     formación
    -0.27
     bag
    -0.27
    FDRE
    -0.26
    Painted
    -0.26
    POSITIVE LOGITS
    Portale
    0.67
     дописавши
    0.65
     disambiguazione
    0.63
     otomatig
    0.60
    httphttps
    0.59
     <<<<<<<<<<<<<<
    0.58
    Chham
    0.58
    IntoConstraints
    0.58
     <>",
    0.58
     Meksiku
    0.56
    Activations Density 0.042%

    No Known Activations