© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6861
    Prev
    Next
    INDEX
    Explanations

    references to evidence and descriptions related to crime scenes

    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
     cejas
    -0.57
     niebla
    -0.57
     ruinas
    -0.57
     bahía
    -0.56
     przód
    -0.51
     Gegend
    -0.51
     fisuras
    -0.51
     exposiciones
    -0.50
     exceso
    -0.49
     refroidissement
    -0.48
    POSITIVE LOGITS
     gloves
    1.45
     pillows
    1.43
     towels
    1.38
     slippers
    1.34
     towel
    1.31
     umbrellas
    1.31
     handker
    1.30
     binoculars
    1.30
     handkerchief
    1.30
     pillow
    1.29
    Activations Density 1.274%

    No Known Activations