© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6667
    Prev
    Next
    INDEX
    Explanations

    instances of the word "blind" as well as phrases relating to blindness or being sightless

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    PerformLayout
    -0.91
     surla
    -0.88
    AppRoutingModule
    -0.75
    المصادر
    -0.72
    ulkner
    -0.69
    SourceChecksum
    -0.69
    eschön
    -0.68
    FormBorderStyle
    -0.68
     समीक्षाओं
    -0.66
     ujednoznacz
    -0.65
    POSITIVE LOGITS
     blind
    1.34
    Blind
    1.27
    blind
    1.24
     Blind
    1.19
     blinds
    1.02
     blindness
    1.00
     nerve
    0.96
     aveug
    0.94
     Nerve
    0.94
     blinding
    0.87
    Activations Density 0.091%

    No Known Activations