© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12407
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and functions related to geometric concepts

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

    The letter "g"

    np_acts-logits-general · gemini-2.0-flash

    g and words starting with G

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    *~*~
    -0.53
    GOTREF
    -0.52
    *}{
    -0.49
     Touchable
    -0.49
     useParams
    -0.47
     onPostExecute
    -0.47
     Niles
    -0.47
    *}[
    -0.45
     gynhyrchwyd
    -0.45
    Rox
    -0.45
    POSITIVE LOGITS
     g
    0.74
     G
    0.74
    ViewInit
    0.67
    G
    0.66
    g
    0.65
    gutter
    0.63
     Gey
    0.63
     Geller
    0.60
     Gart
    0.60
     Ghetto
    0.59
    Activations Density 1.145%

    No Known Activations