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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5126
    Prev
    Next
    INDEX
    Explanations

    patterns related to dietary diversity and food group consumption among different age generations

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

    food group diversity criteria

    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
     intStringLen
    -0.42
    WriteAttribute
    -0.38
     informée
    -0.35
     ModelExpression
    -0.32
    MathML
    -0.32
     CURIAM
    -0.30
    stunde
    -0.30
    Timmy
    -0.30
     Ruhm
    -0.30
     zewnętrzne
    -0.29
    POSITIVE LOGITS
    rungsseite
    0.65
     nahilalakip
    0.58
    writeFieldEnd
    0.54
     îna
    0.53
     kaarangay
    0.52
    Jeografia
    0.52
     للمعارف
    0.51
     împ
    0.48
     möjligt
    0.47
    clerView
    0.46
    Activations Density 0.116%

    No Known Activations