© 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. 34-GEMMASCOPE-RES-16K
    11. 12206
    Prev
    Next
    INDEX
    Explanations

    phrases related to health-related content, research, and legal disclaimers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.63
     विश्वसनीयता
    -0.56
    Rujuakan
    -0.52
    </tfoot>
    -0.49
    errHandler
    -0.48
    󠁿
    -0.48
     invokingState
    -0.48
     المعيارى
    -0.47
    IVEREF
    -0.45
    turnstile
    -0.44
    POSITIVE LOGITS
    ServletConfig
    0.38
    ajemy
    0.36
     lämp
    0.35
    Pairs
    0.35
     zdję
    0.34
     adı
    0.34
    mentaires
    0.33
     Baths
    0.33
     zasi
    0.33
    camisetas
    0.33
    Activations Density 0.767%

    No Known Activations