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
    4. Residual Stream - 131k
    5. 33-GEMMASCOPE-RES-131K
    6. 65801
    Prev
    Next
    INDEX
    Explanations

    elements related to family dynamics and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.74
     فريبيس
    -0.68
     typelib
    -0.66
     defaultstate
    -0.65
    featureID
    -0.65
    Families
    -0.64
     كومونز
    -0.64
    UnusedPrivate
    -0.63
     ब्रेकडाउन
    -0.62
    ftance
    -0.61
    POSITIVE LOGITS
     elkaar
    0.34
     coscienza
    0.32
     partij
    0.32
     Bä
    0.31
     cárcel
    0.30
    uk
    0.30
     kobiet
    0.29
    planung
    0.29
     gambe
    0.28
    //*[@
    0.28
    Activations Density 0.015%

    No Known Activations