© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 56291
    Prev
    Next
    INDEX
    Explanations

    instances of the word "bos" and variations, indicating a focus on structured data or elements within a dataset

    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
     betweenstory
    -1.20
    DoubleQuotes
    -0.83
    AndEndTag
    -0.73
    Personendaten
    -0.72
    HandlerContext
    -0.69
    WebVitals
    -0.65
    ArgsConstructor
    -0.64
    Personensuche
    -0.63
     الحره
    -0.63
    <!--[
    -0.63
    POSITIVE LOGITS
     “
    0.60
     able
    0.57
    virons
    0.54
    tvguidetime
    0.53
     being
    0.49
     “…
    0.48
    ="'
    0.47
    TINGS
    0.47
     amongst
    0.47
     become
    0.47
    Activations Density 0.079%

    No Known Activations