© 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. 20-GEMMASCOPE-RES-16K
    11. 13122
    Prev
    Next
    INDEX
    Explanations

    references to various surface characteristics and textures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pouvoit
    -0.49
    einander
    -0.47
    rollment
    -0.47
    rachtet
    -0.47
     Kredit
    -0.46
     bileklik
    -0.46
     lottery
    -0.46
     Pediatrics
    -0.45
    llog
    -0.45
     annals
    -0.45
    POSITIVE LOGITS
     Surface
    1.16
     surface
    1.15
    Surface
    1.09
     SURFACE
    1.07
    surface
    1.04
    SURFACE
    0.92
    urface
    0.91
     superficie
    0.85
     surfaces
    0.81
     Surfaces
    0.79
    Activations Density 0.085%

    No Known Activations