© 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. 20-GEMMASCOPE-RES-131K
    11. 99553
    Prev
    Next
    INDEX
    Explanations

    references to diets and nutrition, particularly concerning the portrayal of carbohydrates

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

    average consumption of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eng
    -0.29
     operation
    -0.29
     pallets
    -0.28
     Vodafone
    -0.28
     walk
    -0.28
     walked
    -0.27
     premi
    -0.27
     respondent
    -0.26
     négo
    -0.26
     Walk
    -0.26
    POSITIVE LOGITS
     EconPapers
    0.89
    tvguidetime
    0.86
    rungsseite
    0.67
    ьаж
    0.67
    脚注の使い方
    0.66
    TagMode
    0.65
    Lähteet
    0.65
    ruik
    0.64
    AndEndTag
    0.64
     مرئيه
    0.63
    Activations Density 0.028%

    No Known Activations