© 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-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 10568
    Prev
    Next
    INDEX
    Explanations

    sentences with physical actions or elements related to interaction and movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.65
    tanleria
    -0.65
     titolata
    -0.54
    Искәрмәләр
    -0.54
    verifyException
    -0.52
     ddelweddau
    -0.52
     Autorisations
    -0.52
     viață
    -0.51
     vacanze
    -0.50
     مرئيه
    -0.50
    POSITIVE LOGITS
     glasses
    0.45
     goggles
    0.41
     pulled
    0.35
     rubber
    0.35
     pa
    0.34
     equipment
    0.33
     bra
    0.33
     black
    0.33
     wooden
    0.33
     parseFrom
    0.32
    Activations Density 0.692%

    No Known Activations