© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 1911
    Prev
    Next
    INDEX
    Explanations

    references to sexual minority identities and their intersectionality with family dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    läufe
    -0.58
     fiebre
    -0.54
    DockStyle
    -0.52
    ,:),
    -0.50
     gainera
    -0.48
    deauna
    -0.48
    Condol
    -0.48
    武将
    -0.47
     Fazit
    -0.47
    gantung
    -0.46
    POSITIVE LOGITS
     psychologists
    0.67
     Bakan
    0.59
     psychologist
    0.57
     Psychologist
    0.56
     inappro
    0.55
     psic
    0.55
    #+#
    0.54
     propOrder
    0.53
     psicológico
    0.53
    motic
    0.52
    Activations Density 0.758%

    No Known Activations