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

    Neuronpedia

    Jacobian LensNEW
    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. 22-GEMMASCOPE-RES-16K
    11. 1910
    Prev
    Next
    INDEX
    Explanations

    actions and interactions that convey physical sensations or intimate moments

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

    Action following a character's name

    np_acts-logits-general · gemini-2.0-flash

    she was

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.60
     terecht
    -0.60
     walks
    -0.58
    Visiting
    -0.57
     Réponses
    -0.56
    BIND
    -0.55
    allible
    -0.55
     arrivant
    -0.54
     Walks
    -0.53
    walks
    -0.53
    POSITIVE LOGITS
     mutter
    0.75
     scream
    0.69
     shout
    0.67
     wig
    0.65
     muttering
    0.65
     continuously
    0.65
     whisper
    0.64
     yell
    0.64
     yelling
    0.63
     chanting
    0.62
    Activations Density 0.255%

    No Known Activations