© 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. 9823
    Prev
    Next
    INDEX
    Explanations

    mentions of authorship or references to authors in research 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
    はじめに
    -0.51
    sstream
    -0.51
    flink
    -0.48
    AddTagHelper
    -0.46
    chyma
    -0.46
    MeasureSpec
    -0.46
     handleClick
    -0.45
    guntas
    -0.45
    esség
    -0.44
    useEffect
    -0.44
    POSITIVE LOGITS
     author
    4.16
     Author
    3.94
    Author
    3.75
    author
    3.69
     AUTHOR
    3.53
     authors
    3.50
    AUTHOR
    3.34
     Authors
    3.23
    authors
    3.08
    Authors
    2.94
    Activations Density 0.042%

    No Known Activations