© 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. 35-GEMMASCOPE-RES-16K
    11. 7269
    Prev
    Next
    INDEX
    Explanations

    actions and interactions of a sexual nature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Liebe
    -0.38
    CLAIMER
    -0.36
     иначе
    -0.36
     otherwise
    -0.33
     Hütte
    -0.32
    ceğine
    -0.32
    ExternalTask
    -0.31
    buatan
    -0.30
    ütfen
    -0.30
    ca
    -0.30
    POSITIVE LOGITS
     fingers
    0.68
    UnusedPrivate
    0.65
     finger
    0.62
    RectangleBorder
    0.61
    GOTREF
    0.59
    findpost
    0.58
     index
    0.57
     fists
    0.57
    typeorm
    0.56
     hands
    0.54
    Activations Density 0.304%

    No Known Activations