© 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-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 9820
    Prev
    Next
    INDEX
    Explanations

    conjunctions, specifically the word "and" in various contexts

    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
     ―――――
    -1.47
     ainfi
    -1.41
     auffi
    -1.39
     $_"
    -1.37
     Efq
    -1.36
     itſelf
    -1.33
     doubtnut
    -1.31
     myſelf
    -1.30
     auroit
    -1.30
     ſind
    -1.27
    POSITIVE LOGITS
    .
    1.04
     (
    1.02
    ↵
    1.02
    ↵↵
    1.00
      
    0.93
     in
    0.91
     is
    0.89
    ,
    0.85
    -
    0.84
     on
    0.84
    Activations Density 0.143%

    No Known Activations