© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 35365
    Prev
    Next
    INDEX
    Explanations

    references to fat and its distribution in the context of obesity and related health metrics

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

    fat, adipose tissue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.53
     zijne
    -0.48
    المناصب
    -0.47
     Infórmanos
    -0.47
     demokra
    -0.44
    InitVars
    -0.43
     miniaturka
    -0.43
     terapé
    -0.43
    曖昧さ回避
    -0.42
     autorytatywna
    -0.42
    POSITIVE LOGITS
     fat
    0.71
     الحره
    0.63
     fatty
    0.59
     adipose
    0.58
     Fat
    0.58
    fat
    0.57
     adipo
    0.56
    Fat
    0.56
    PropertyChanging
    0.56
     esterni
    0.55
    Activations Density 0.122%

    No Known Activations