© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 55186
    Prev
    Next
    INDEX
    Explanations

    references to gay identities and experiences

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

    gay identity, groups,

    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
     للاسماء
    -0.54
    ceptre
    -0.50
     protectors
    -0.49
    NOO
    -0.48
     Lumi
    -0.46
    CEPT
    -0.46
    itola
    -0.46
    運び
    -0.45
     NCC
    -0.45
     nơi
    -0.45
    POSITIVE LOGITS
     gay
    0.99
     GAY
    0.93
    Gay
    0.84
     Gay
    0.82
     homosexual
    0.82
    gay
    0.78
     gays
    0.75
    osexual
    0.68
     lesbian
    0.68
    mobileqq
    0.60
    Activations Density 0.008%

    No Known Activations