© 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. 35-GEMMASCOPE-RES-16K
    11. 13553
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries about beliefs, expectations, and clarifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    felizmente
    -0.51
     насељу
    -0.51
    gebraucht
    -0.50
     '*':
    -0.49
    tagez
    -0.49
    onOptions
    -0.48
     endregion
    -0.46
     BoxFit
    -0.46
    EndGlobal
    -0.45
    DOCTYPE
    -0.44
    POSITIVE LOGITS
     exactly
    0.96
    exactly
    0.79
    Exactly
    0.77
     exatamente
    0.76
     Exactly
    0.72
     exactamente
    0.70
     exactement
    0.66
     precies
    0.65
     esattamente
    0.62
     supposed
    0.59
    Activations Density 0.445%

    No Known Activations