© 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 EvalsExportsinterp-engineNEWAPI 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. 9493
    Prev
    Next
    INDEX
    Explanations

    assumptions related to data models and their limitations

    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
    rungsseite
    -0.60
     Timeline
    -0.51
    WireFormatLite
    -0.46
     Sequ
    -0.46
     timeline
    -0.46
     Ena
    -0.45
     Chron
    -0.44
    Timeline
    -0.44
     Centr
    -0.44
     Pion
    -0.43
    POSITIVE LOGITS
     Aussage
    0.57
     Ausgleich
    0.57
     raisonnable
    0.55
     reasonable
    0.52
     Vernunft
    0.51
    HomeAsUpEnabled
    0.51
     perilaku
    0.50
     Verbesserung
    0.50
     computationally
    0.50
     representación
    0.50
    Activations Density 2.640%

    No Known Activations