© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 4323
    Prev
    Next
    INDEX
    Explanations

    references to coding or programming elements, especially those involving underscores and wildcard characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vikipedi
    -0.72
     endforeach
    -0.67
     faſt
    -0.65
     foon
    -0.64
    ViewChild
    -0.62
    tagHelperRunner
    -0.61
    aarrggbb
    -0.61
    NewRow
    -0.60
    LayoutConstraint
    -0.60
    Autoritní
    -0.59
    POSITIVE LOGITS
     damn
    0.62
     entier
    0.60
    (!)
    0.57
     (!)
    0.56
     absolutely
    0.54
     itself
    0.53
     absolument
    0.53
     nữa
    0.52
     (!
    0.52
     really
    0.51
    Activations Density 0.142%

    No Known Activations