© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 9816
    Prev
    Next
    INDEX
    Explanations

    nouns related to objects or entities within a given context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     légales
    -0.80
    extrait
    -0.70
    BZ
    -0.62
     extrait
    -0.62
     brune
    -0.61
     industriale
    -0.61
     Eller
    -0.61
     desto
    -0.60
    Kariera
    -0.60
     militare
    -0.59
    POSITIVE LOGITS
     Ham
    0.78
     Eng
    0.74
     hack
    0.68
     ENG
    0.68
    Eng
    0.67
     ham
    0.64
     hacks
    0.62
    Hack
    0.61
    hack
    0.61
     fountain
    0.60
    Activations Density 0.036%

    No Known Activations