© 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. 6190
    Prev
    Next
    INDEX
    Explanations

    references to the word "dozen" and related terms like "graduate."

    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
    出版年
    -0.62
    ValueStyle
    -0.58
    PDOException
    -0.54
    makeConstraints
    -0.54
    AddField
    -0.53
    بالإنجليزية
    -0.53
    <?
    -0.53
    smithy
    -0.53
     Timberlake
    -0.52
    THOOK
    -0.51
    POSITIVE LOGITS
     creature
    0.74
     dozen
    0.67
    creature
    0.60
     creatures
    0.57
     operator
    0.56
    +#+
    0.55
     Creature
    0.55
    Creature
    0.54
     beings
    0.53
    dozen
    0.53
    Activations Density 0.061%

    No Known Activations