© 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. 14393
    Prev
    Next
    INDEX
    Explanations

    technical terms related to electronics and circuit components

    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
    -0.39
     currents
    -0.38
     جاری
    -0.38
     corrente
    -0.37
     Kraw
    -0.36
    Viited
    -0.35
    adpleegd
    -0.35
     bate
    -0.34
     channels
    -0.34
     Laub
    -0.34
    POSITIVE LOGITS
     Capac
    0.95
    capac
    0.92
    Capac
    0.90
     capacitance
    0.84
     capacitor
    0.84
     Capacitor
    0.81
     capacitors
    0.79
     kapas
    0.77
    Cap
    0.71
    capacity
    0.68
    Activations Density 0.318%

    No Known Activations