Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 92886
    Prev
    Next
    INDEX
    Explanations

    names of people and their associations

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

    Jared Kushner, Eaton, Chopra, married spouses

    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
     iParam
    -0.29
    gestaltung
    -0.28
     fundos
    -0.28
    lude
    -0.28
     dök
    -0.27
     şeyler
    -0.27
    cat
    -0.26
     viņ
    -0.26
    height
    -0.25
     amizade
    -0.25
    POSITIVE LOGITS
     married
    0.88
     Wife
    0.84
    Wife
    0.83
     wife
    0.81
     husband
    0.81
     Administrativna
    0.81
    married
    0.79
     Married
    0.78
     spouses
    0.75
    Married
    0.74
    Activations Density 0.023%

    No Known Activations