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. 3-GEMMASCOPE-RES-16K
    6. 8373
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and requests for help

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ...',
    -0.54
    (),
    
    -0.52
    ()].
    -0.52
    ...";
    -0.51
    ...),
    -0.50
     Tali
    -0.49
    erati
    -0.48
    ...");
    -0.47
    |}{$
    -0.47
    τον
    -0.47
    POSITIVE LOGITS
    Cheers
    0.87
    Regards
    0.84
    cheers
    0.81
    Pozdrawiam
    0.81
    Cordialement
    0.78
    Děkuji
    0.77
     ExecuteAsync
    0.76
     Cheers
    0.73
    Thanks
    0.73
    localctx
    0.73
    Activations Density 0.175%

    No Known Activations