© 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 EvalsExportsinterp-engineNEWAPI 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. 8152
    Prev
    Next
    INDEX
    Explanations

    linguistic features and patterns in structured data, including timestamps and format identifiers

    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
    ↵↵
    -1.73
    <eos>
    -1.68
    ↵
    -1.58
     (
    -1.52
     
    -1.37
    a
    -1.35
    y
    -1.29
    i
    -1.28
    .
    -1.27
    in
    -1.26
    POSITIVE LOGITS
     Efq
    2.63
     myſelf
    2.50
     Majefty
    2.45
     Monfieur
    2.36
     Houſe
    2.34
     houſe
    2.31
     itſelf
    2.31
     purpoſe
    2.28
     Jefus
    2.28
     Anſ
    2.20
    Activations Density 1.377%

    No Known Activations