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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 16305
    Prev
    Next
    INDEX
    Explanations

    references to women and their relationships, particularly emphasizing the significance of wives and romantic connections

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

    females ("woman", "wife", "girl", "Queen")

    np_acts-logits-general · gemini-2.0-flash

    wife, woman, girl, Queen

    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
    зыка
    -0.34
     deği
    -0.33
     चीज़ों
    -0.33
     kulak
    -0.32
    esterno
    -0.32
    importanza
    -0.32
    umpf
    -0.31
     Lup
    -0.31
     reflexão
    -0.31
    вец
    -0.31
    POSITIVE LOGITS
    帖最后由
    0.67
    setVerticalGroup
    0.63
     uLocal
    0.59
    ItemBackground
    0.59
    󠁴
    0.57
     Италијани
    0.56
    TypedDataSet
    0.56
    ChildScrollView
    0.55
    RTEX
    0.55
    ISupport
    0.54
    Activations Density 0.436%

    No Known Activations