© 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 - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 7746
    Prev
    Next
    INDEX
    Explanations

    textually referenced words and phrases, possibly for verification or confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zło
    -0.57
    mmate
    -0.52
    WriteLiteral
    -0.52
    ,:);
    -0.52
     oaks
    -0.51
    ẹp
    -0.51
     avanzada
    -0.50
     potrivit
    -0.50
    Anlage
    -0.50
     tunnels
    -0.49
    POSITIVE LOGITS
    MessageOf
    0.67
    SharedDtor
    0.57
    Famille
    0.56
    httphttps
    0.56
     Administrativna
    0.55
    abetes
    0.54
    routeProvider
    0.54
     ligiloj
    0.54
    webElementXpaths
    0.54
    =$?
    0.53
    Activations Density 0.045%

    No Known Activations