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. 11-GEMMASCOPE-RES-16K
    6. 13128
    Prev
    Next
    INDEX
    Explanations

    references to common or typical concepts and instances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chad
    -0.82
    o
    -0.74
     отношению
    -0.74
     Cardona
    -0.74
    ा
    -0.71
    İstinadlar
    -0.71
     Lutz
    -0.69
    HtmlAttribute
    -0.69
    makeText
    -0.68
     المعيارى
    -0.68
    POSITIVE LOGITS
    theless
    0.95
    etheless
    0.84
    ✨:
    0.84
    &=&\
    0.78
     plufieurs
    0.77
     Occasion
    0.76
    Vener
    0.75
     Hv
    0.75
     Dage
    0.75
     (
    
    0.74
    Activations Density 0.444%

    No Known Activations