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. 20-GEMMASCOPE-RES-131K
    6. 53849
    Prev
    Next
    INDEX
    Explanations

    references to marginalized groups and their experiences with oppression and systemic injustice

    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_20/width_131k/average_l0_114
    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
    styleType
    -0.35
    accro
    -0.33
    ciatore
    -0.33
     surprising
    -0.32
    NotEqualTo
    -0.32
     easy
    -0.31
     Handicapped
    -0.30
    某
    -0.30
     remar
    -0.30
     surprisingly
    -0.29
    POSITIVE LOGITS
     الرياضيه
    0.66
    İstinadlar
    0.66
    AsUp
    0.54
    addCriterion
    0.54
     Roskov
    0.52
    AndEndTag
    0.51
     '\\;'
    0.49
    XmlIgnore
    0.49
    Спасылкі
    0.49
    wantErr
    0.48
    Activations Density 0.027%

    No Known Activations