© 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 - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 11609
    Prev
    Next
    INDEX
    Explanations

    references to academic articles and their publication details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stille
    -0.47
     silêncio
    -0.47
     anything
    -0.46
     giù
    -0.45
    翻攝
    -0.44
     dAtA
    -0.44
    ăți
    -0.44
     Anything
    -0.43
     alphabetically
    -0.43
    createCell
    -0.42
    POSITIVE LOGITS
    __':
    
    0.75
     disambiguazione
    0.74
    脚注の使い方
    0.69
    __":
    
    0.61
    )++;
    0.60
    falgar
    0.59
    Capítulo
    0.58
    enderror
    0.58
     autorytatywna
    0.57
    ArrowToggle
    0.57
    Activations Density 0.274%

    No Known Activations