© 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. 20-GEMMASCOPE-RES-16K
    6. 13728
    Prev
    Next
    INDEX
    Explanations

    properties and characteristics of objects or materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    physical properties that describe thinness or openness, like "light", "slender", "transparent", or "gaps".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    stationary
    -0.59
     Савезне
    -0.59
    +#+#
    -0.51
    versiti
    -0.50
     Pij
    -0.49
    ooker
    -0.49
    omyces
    -0.48
     prywat
    -0.48
    orologio
    -0.48
     stationary
    -0.47
    POSITIVE LOGITS
     thin
    0.56
     Thin
    0.54
     airy
    0.52
     open
    0.50
     lightness
    0.50
    Thin
    0.49
     lightly
    0.48
     Lightweight
    0.45
     Open
    0.44
     flimsy
    0.44
    Activations Density 0.421%

    No Known Activations