© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105004
    Prev
    Next
    INDEX
    Explanations

    instances of the term "clue" along with references to specific journals or publications

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     noDo
    -0.71
    Portail
    -0.62
    帖最后由
    -0.60
     Infórmanos
    -0.57
     GenerationType
    -0.55
     Վերցված
    -0.54
    醐
    -0.53
    postdata
    -0.52
    minecraftforge
    -0.52
    wapV
    -0.52
    POSITIVE LOGITS
     Blen
    0.54
    Clu
    0.52
     clots
    0.50
     Clough
    0.50
    chengladbach
    0.50
     Blouse
    0.49
     Clu
    0.49
    Clash
    0.48
    Clon
    0.48
     fileList
    0.48
    Activations Density 0.092%

    No Known Activations