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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 3573
    Prev
    Next
    INDEX
    Explanations

    structural elements and closing tags in HTML or similar markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 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
     препратки
    -0.52
     barri
    -0.48
    ſelf
    -0.48
     viſ
    -0.48
    addPreferredGap
    -0.46
     ſind
    -0.46
     unſ
    -0.45
     eſſ
    -0.45
     faſt
    -0.45
    mitter
    -0.44
    POSITIVE LOGITS
     endwhile
    0.49
     EconPapers
    0.44
     disambiguazione
    0.43
    endwhile
    0.43
    DataContract
    0.42
    BagConstraints
    0.41
    EndContext
    0.39
    RTCK
    0.39
     виправивши
    0.38
    AllowAnonymous
    0.38
    Activations Density 0.647%

    No Known Activations