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. 21-GEMMASCOPE-RES-16K
    6. 15053
    Prev
    Next
    INDEX
    Explanations

    conversational phrases and expressions of opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.78
    zzleHttp
    -0.73
    İstinadlar
    -0.69
    ThroughAttribute
    -0.69
     بتاريخ
    -0.68
    ]--;
    -0.68
    GOTREF
    -0.67
     StatefulWidget
    -0.67
    webElementXpaths
    -0.67
    abetes
    -0.66
    POSITIVE LOGITS
     would
    3.89
    would
    3.35
     Would
    3.09
    Would
    2.97
     WOULD
    2.80
     wouldn
    2.33
    wouldn
    2.03
     zou
    1.89
     zouden
    1.89
     wouldnt
    1.88
    Activations Density 1.460%

    No Known Activations