© 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-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 7897
    Prev
    Next
    INDEX
    Explanations

    specific numerical identifiers and references within scientific or academic citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Slf
    -0.43
     yine
    -0.43
    ină
    -0.40
    同じく
    -0.38
     също
    -0.38
     NSCoder
    -0.38
     Erişim
    -0.37
     simplifié
    -0.37
    enes
    -0.37
    nė
    -0.37
    POSITIVE LOGITS
    IUrlHelper
    0.63
    SourceChecksum
    0.60
     kasarigan
    0.60
     ſta
    0.59
     ſur
    0.58
    awaiter
    0.57
     faſt
    0.56
    aarrggbb
    0.54
     pinulongan
    0.52
     ſte
    0.52
    Activations Density 1.075%

    No Known Activations