© 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. 0-GEMMASCOPE-RES-16K
    6. 6065
    Prev
    Next
    INDEX
    Explanations

    references to various editions of publications, particularly focusing on "edition" as a keyword

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olybden
    -0.54
     nominations
    -0.48
    IBILITIES
    -0.47
     Consist
    -0.47
     nomin
    -0.45
    違います
    -0.44
     ucapnya
    -0.44
    falen
    -0.44
     nomination
    -0.44
    Appreciate
    -0.43
    POSITIVE LOGITS
    mail
    0.90
    Mail
    0.86
    migrationBuilder
    0.86
     pop
    0.79
    ArgsConstructor
    0.77
    ]--;
    0.74
     Mail
    0.74
    MAIL
    0.73
    型
    0.73
     Edition
    0.70
    Activations Density 0.116%

    No Known Activations