© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 4054
    Prev
    Next
    INDEX
    Explanations

    specific technical or mathematical terms related to transformation and quantization processes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ore
    -0.60
    ow
    -0.57
    ote
    -0.57
    ors
    -0.57
    ows
    -0.56
    oman
    -0.56
    oid
    -0.56
    oon
    -0.56
    oun
    -0.56
    antly
    -0.56
    POSITIVE LOGITS
    hygiène
    0.39
    indépendance
    0.38
    émission
    0.35
    amitié
    0.33
    humanité
    0.33
    ない
    0.33
    k
    0.33
    accompagnement
    0.33
    assemblée
    0.33
    interprétation
    0.33
    Activations Density 4.527%

    No Known Activations