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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 12315
    Prev
    Next
    INDEX
    Explanations

    mentions of marginalized or minority groups and their experiences, particularly in relation to race and diversity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rzost
    -0.39
     Senado
    -0.37
     résult
    -0.37
     Pist
    -0.37
     VIG
    -0.37
     vig
    -0.37
     LUCK
    -0.36
     Hoon
    -0.35
     vaikka
    -0.35
    DISPATCH
    -0.35
    POSITIVE LOGITS
    ⟬
    0.58
     LGBTQ
    0.56
     lgbt
    0.56
    featureID
    0.55
     Jews
    0.54
    Билгалдахарш
    0.53
    LGBT
    0.53
    ScopeManager
    0.52
    #+#
    0.50
     LGBT
    0.49
    Activations Density 0.650%

    No Known Activations