© 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-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 7678
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically semicolons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mpagne
    -1.12
     ſind
    -1.11
    majánló
    -1.09
    uxxxx
    -1.09
    ſcher
    -1.05
     ſei
    -1.05
    ſehen
    -1.05
    iſten
    -1.05
    ésultats
    -1.04
     queſta
    -1.04
    POSITIVE LOGITS
    ;
    2.44
    ;
    
    1.56
     ;
    1.49
    ;
    1.38
    .;
    1.38
    );
    1.22
    ;;
    1.21
    $;
    1.20
    ';
    1.19
    ?;
    1.17
    Activations Density 0.215%

    No Known Activations