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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 7968
    Prev
    Next
    INDEX
    Explanations

    references to prizes and specific dosage measurements in milligrams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oredCriteria
    -0.48
    endregion
    -0.45
     окружа
    -0.42
     ogrodow
    -0.42
     automne
    -0.41
    angry
    -0.40
    worfen
    -0.40
     voici
    -0.39
    mergeFrom
    -0.39
     nôtre
    -0.39
    POSITIVE LOGITS
     prize
    0.82
     sprite
    0.79
     Sprite
    0.77
    sprite
    0.71
     magistrate
    0.70
     Prize
    0.69
    Prize
    0.68
     PRIZE
    0.68
    Sprite
    0.67
     Alias
    0.65
    Activations Density 0.111%

    No Known Activations