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

    Neuronpedia

    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. 10-GEMMASCOPE-RES-16K
    11. 7283
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting elements typically found in structured data or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -0.82
     Chwiliwch
    -0.78
     فريبيس
    -0.72
    PMailer
    -0.70
    OGND
    -0.68
     AssemblyTitle
    -0.66
     GenerationType
    -0.64
    parsedMessage
    -0.63
     Efq
    -0.63
     AssemblyCompany
    -0.63
    POSITIVE LOGITS
    rceil
    0.63
    ⌉
    0.50
    rfloor
    0.46
     ever
    0.44
    endphp
    0.43
    〉
    0.42
    AutoModerator
    0.40
    rrbracket
    0.39
    endsection
    0.36
    ⟩
    0.36
    Activations Density 1.729%

    No Known Activations