© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8334
    Prev
    Next
    INDEX
    Explanations

    HTML tags and formatting indicating emphasis in text

    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
     
    -2.27
    ,
    -2.13
     in
    -2.05
    .
    -2.02
     (
    -1.97
     a
    -1.82
     to
    -1.77
    '
    -1.74
    /
    -1.73
     of
    -1.71
    POSITIVE LOGITS
     myſelf
    3.92
     itſelf
    3.77
     Efq
    3.58
     Monfieur
    3.31
     Theſe
    3.30
     ―――――
    3.27
     doubtnut
    3.22
     Jefus
    3.13
     Majefty
    3.11
    ſelves
    3.09
    Activations Density 0.003%

    No Known Activations