© 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. 7188
    Prev
    Next
    INDEX
    Explanations

    evidence of evolutionary adaptive responses to seasonal and spatial variations in environmental pressures

    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
     surla
    -0.61
    ChrTalk
    -0.61
     препратки
    -0.57
     ProtoMessage
    -0.52
    findpost
    -0.52
    ⓧ
    -0.50
    новниш
    -0.50
    fillType
    -0.49
     actionPerformed
    -0.48
    Życiorys
    -0.48
    POSITIVE LOGITS
     fitness
    0.47
     Fitness
    0.42
     foraging
    0.40
    Fitness
    0.40
     individuals
    0.40
    個
    0.40
     ecologically
    0.39
     sex
    0.38
     cryptic
    0.38
     ecological
    0.38
    Activations Density 1.815%

    No Known Activations