© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 4041
    Prev
    Next
    INDEX
    Explanations

    instances of the word "see" or its variations indicating perception or observation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    athus
    -0.46
     התק
    -0.42
    rantz
    -0.38
     lingue
    -0.36
     Gru
    -0.36
    ulent
    -0.36
     linguistique
    -0.35
    localctx
    -0.34
     lingu
    -0.34
     twij
    -0.34
    POSITIVE LOGITS
    Seen
    1.04
     see
    1.03
    see
    1.02
    Saw
    0.99
    See
    0.97
     sees
    0.96
    seen
    0.95
    saw
    0.95
     See
    0.91
     SEE
    0.91
    Activations Density 0.190%

    No Known Activations