© 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. 21-GEMMASCOPE-RES-16K
    11. 10395
    Prev
    Next
    INDEX
    Explanations

    instances of communication and significant events

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ❋
    -0.48
     golfe
    -0.46
    providedIn
    -0.45
     idee
    -0.45
    cookieParser
    -0.45
     formules
    -0.44
     الرياضيه
    -0.44
     charité
    -0.44
    Yummy
    -0.43
     Sénégal
    -0.42
    POSITIVE LOGITS
     suddenly
    0.66
     sudden
    0.60
     Suddenly
    0.55
     abruptly
    0.55
     announcement
    0.54
    suddenly
    0.52
    Suddenly
    0.51
     news
    0.51
     plötzlich
    0.50
     notification
    0.48
    Activations Density 0.307%

    No Known Activations