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 - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15533
    Prev
    Next
    INDEX
    Explanations

    mentions of prominent figures in the LGBTQ+ community and their advocacy

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

    "pageant" or "user" tokens

    np_acts-logits-general · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infórmanos
    -0.48
    AndroidJUnit
    -0.45
    pieler
    -0.43
    لينكات
    -0.42
     يتيمه
    -0.40
     bambú
    -0.40
     Wärme
    -0.40
    WithMany
    -0.39
     Wikiseite
    -0.37
    agaimana
    -0.37
    POSITIVE LOGITS
     Miss
    1.26
     pageant
    1.23
    Miss
    1.15
     beauty
    1.09
     Beauty
    1.02
    beauty
    1.01
    Beauty
    0.97
     miss
    0.96
     crown
    0.95
     contestants
    0.93
    Activations Density 0.023%

    No Known Activations