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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 22467
    Prev
    Next
    INDEX
    Explanations

    structural elements or markers in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    -0.55
     or
    -0.54
     ou
    -0.49
     U
    -0.48
     best
    -0.48
     (
    -0.47
    <u>
    -0.46
     -
    -0.45
     is
    -0.45
     most
    -0.44
    POSITIVE LOGITS
     wireType
    1.09
    IntoConstraints
    1.02
     purpoſe
    0.99
     Efq
    0.98
    apimachinery
    0.98
     Anſ
    0.95
     myſelf
    0.95
     fevere
    0.93
     Theſe
    0.91
     propOrder
    0.90
    Activations Density 0.008%

    No Known Activations