© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 6583
    Prev
    Next
    INDEX
    Explanations

    references to health, fitness, and body measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words and phrases related to body weight, size, and physical appearance.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.60
     ExecuteAsync
    -0.53
    Cyfarwyddwr
    -0.52
     ब्रेकडाउन
    -0.52
    ьаж
    -0.50
    帖最后由
    -0.49
    yntaxException
    -0.48
     فريبيس
    -0.48
     ویکی‌آمباردا
    -0.48
    fitrión
    -0.47
    POSITIVE LOGITS
     slim
    1.20
     slimming
    1.12
    slim
    1.01
     skinny
    0.96
     Slim
    0.94
     slender
    0.94
     fat
    0.91
     waist
    0.89
    Slim
    0.89
    skinny
    0.82
    Activations Density 0.177%

    No Known Activations