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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8813
    Prev
    Next
    INDEX
    Explanations

    topics related to individual beliefs and freedoms, particularly in the context of marriage and religion

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

    individual liberty and choices

    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
     Administrativna
    -0.71
    msgTypes
    -0.66
    adaptiveStyles
    -0.57
    IVEREF
    -0.54
    Personensuche
    -0.52
    SourceChecksum
    -0.50
    parsedMessage
    -0.50
    toHaveBeen
    -0.49
     Numerade
    -0.47
    expandindo
    -0.47
    POSITIVE LOGITS
     persoane
    0.35
     voisins
    0.31
    μως
    0.31
    hésite
    0.31
     nariz
    0.30
     quienes
    0.30
     ingenting
    0.29
     libertà
    0.29
     diyor
    0.29
     partage
    0.28
    Activations Density 0.060%

    No Known Activations