© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 3479
    Prev
    Next
    INDEX
    Explanations

    references to sight or vision

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dummy
    -0.40
     boire
    -0.36
    rungsseite
    -0.35
     ve
    -0.35
     zove
    -0.32
     perpé
    -0.32
     illegal
    -0.32
     Toxic
    -0.31
    Toxic
    -0.31
    Fake
    -0.30
    POSITIVE LOGITS
     sight
    1.23
    sight
    1.05
     Sight
    0.95
     sights
    0.86
    sights
    0.84
    Sight
    0.81
     sighted
    0.67
     Partially
    0.64
     partially
    0.64
    RectangleBorder
    0.63
    Activations Density 0.145%

    No Known Activations