© 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. 36-GEMMASCOPE-RES-16K
    11. 8793
    Prev
    Next
    INDEX
    Explanations

    quantitative data and expressions of frequency, particularly in relation to health behaviors and demographics

    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
     Infórmanos
    -0.52
     Roskov
    -0.50
    SharedCtor
    -0.48
    PreInfinity
    -0.48
    WireFormatLite
    -0.47
     ویکی‌پدیای
    -0.46
     referenties
    -0.45
    帖最后由
    -0.44
    GEBURTS
    -0.44
    balleur
    -0.44
    POSITIVE LOGITS
     quarter
    1.38
     thirds
    1.29
    quarter
    1.15
     Drittel
    1.15
     third
    1.15
    thirds
    1.11
    third
    1.09
     tercio
    1.08
    ⅓
    1.00
     terzo
    0.98
    Activations Density 0.472%

    No Known Activations