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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 539
    Prev
    Next
    INDEX
    Explanations

    references to LGBTQ+ rights and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.64
    Diweddarwch
    -0.60
     recul
    -0.58
    featureID
    -0.57
    ंदीखरीदारी
    -0.56
     '\\;'
    -0.56
    BagConstraints
    -0.56
    amaha
    -0.56
    opolis
    -0.53
     StringTokenizer
    -0.53
    POSITIVE LOGITS
     gay
    2.02
     LGBT
    1.84
     LGBTQ
    1.77
    gay
    1.74
     homosexual
    1.70
     gays
    1.68
    LGBT
    1.66
     lesbian
    1.66
     Gay
    1.62
     queer
    1.62
    Activations Density 0.193%

    No Known Activations