© 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. 12-GEMMASCOPE-RES-16K
    11. 8180
    Prev
    Next
    INDEX
    Explanations

    mathematical and statistical variables and symbols in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rhestr
    -0.66
     propOrder
    -0.64
     autorytatywna
    -0.63
    tagHelperRunner
    -0.63
     Comprometido
    -0.63
    Personendaten
    -0.56
    StoryboardSegue
    -0.55
    تقاوى
    -0.55
     мәкал
    -0.55
    TagMode
    -0.53
    POSITIVE LOGITS
    .
    0.50
     Inspection
    0.46
     ITA
    0.45
     Lazy
    0.44
    [^
    0.44
     trick
    0.43
    жан
    0.43
     Itinerary
    0.43
     Tv
    0.43
     Trial
    0.43
    Activations Density 1.580%

    No Known Activations