© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 13109
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the rarity or unusualness of medical conditions or specific cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.75
    parsedMessage
    -0.71
    MigrationBuilder
    -0.63
    rrggbb
    -0.62
    MessageTagHelper
    -0.61
    JspWriter
    -0.60
    Hozzáférés
    -0.59
     مشين
    -0.57
     lenker
    -0.56
     resourceCulture
    -0.56
    POSITIVE LOGITS
     rare
    3.02
    Rare
    2.55
    rare
    2.53
     Rare
    2.39
     rarity
    2.36
     rares
    2.31
     rarely
    2.30
     rarer
    2.30
     RARE
    2.28
     rarest
    2.20
    Activations Density 1.015%

    No Known Activations