© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13148
    Prev
    Next
    INDEX
    Explanations

    references to personal or group interests and their importance in various contexts

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

    "interests," "gain," or "best" followed by a proposition

    np_acts-logits-general · gemini-2.0-flash

    interests and welfare

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ngdoc
    -0.45
    ########.
    -0.45
     cre
    -0.38
    matchCondition
    -0.35
    cupertino
    -0.34
     amide
    -0.34
    /*++
    -0.33
     tou
    -0.33
     autoradio
    -0.33
     windows
    -0.32
    POSITIVE LOGITS
     welfare
    0.67
     kepentingan
    0.66
     intérêts
    0.62
    transQ
    0.62
     Welfare
    0.60
    welfare
    0.60
     bienestar
    0.58
    Welfare
    0.58
     interests
    0.56
     Numerade
    0.55
    Activations Density 0.276%

    No Known Activations