Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 6483
    Prev
    Next
    INDEX
    Explanations

    instances of the start of a document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     faſt
    -0.80
    ...";
    -0.80
    ...");
    
    -0.80
     iſt
    -0.79
     Arhivirano
    -0.75
     raiſ
    -0.73
    .";
    
    -0.72
     ―――――
    -0.71
    økt
    -0.70
     插图
    -0.70
    POSITIVE LOGITS
    //
    0.70
     Chwiliwch
    0.68
     ت
    0.65
    春日
    0.65
    URLEncoder
    0.65
    évaluateur
    0.65
     inter
    0.64
    脚注の使い方
    0.64
     و
    0.64
    δια
    0.63
    Activations Density 0.034%

    No Known Activations