© 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. 3-GEMMASCOPE-RES-16K
    11. 8580
    Prev
    Next
    INDEX
    Explanations

    terms related to blindness and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.55
    ppuden
    -0.52
    uyasha
    -0.50
    AccessorTable
    -0.49
     indietro
    -0.46
    Sasuke
    -0.44
     OnInit
    -0.43
    psilon
    -0.43
    IANCE
    -0.43
     Dage
    -0.43
    POSITIVE LOGITS
     blind
    1.18
     Blind
    1.09
    Blind
    1.08
    blind
    1.05
    盲
    0.81
     blindness
    0.79
     highlight
    0.78
     blinds
    0.76
     aveug
    0.75
     Highlight
    0.68
    Activations Density 0.067%

    No Known Activations