© 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. 16756
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of institutions and locations

    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
     
    -0.82
    …
    -0.79
    <eos>
    -0.79
    .
    -0.78
     (
    -0.71
     a
    -0.71
    ...
    -0.71
     i
    -0.68
     –
    -0.66
    ↵↵
    -0.65
    POSITIVE LOGITS
     myſelf
    1.19
    ConstraintMaker
    1.16
     itſelf
    1.15
     iſt
    1.10
     ་་
    1.08
     raiſ
    1.06
     auffi
    1.05
     Monfieur
    1.05
     ſever
    1.05
     Theſe
    1.03
    Activations Density 0.025%

    No Known Activations