© 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. 15-GEMMASCOPE-RES-16K
    11. 1352
    Prev
    Next
    INDEX
    Explanations

    LaTeX document structural elements, specifically related to the 'center' environment for formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UseVisualStyle
    -0.93
     iParam
    -0.89
     bParam
    -0.88
    ########.
    -0.88
    ,$_
    -0.83
    endpush
    -0.77
     Weis
    -0.77
    tinyos
    -0.77
     transfieras
    -0.76
     lenker
    -0.75
    POSITIVE LOGITS
    ↵
    0.73
     pector
    0.65
     centerline
    0.56
    center
    0.56
     fermés
    0.55
    0.55
     exciter
    0.55
     plagioclase
    0.54
     dolayı
    0.52
     desertion
    0.52
    Activations Density 0.038%
    No Known Activations