© 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. 13932
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names and well-defined entities in legal or formal contexts

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

    that are all-caps

    np_acts-logits-general · gemini-2.0-flash

    judges, lessons, or technical terms

    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
     المعيارى
    -0.71
    ագրություններ
    -0.66
     desmotivaciones
    -0.63
    ragalactic
    -0.63
     يتيمه
    -0.62
     zuſammen
    -0.62
    Ligações
    -0.60
     Normdatei
    -0.59
     lecciones
    -0.58
    enumi
    -0.58
    POSITIVE LOGITS
     gql
    0.51
    !
    0.41
    Referencie
    0.40
    JA
    0.37
    !!!
    0.37
    ™
    0.36
    AD
    0.36
    ZH
    0.36
    FFFFFFFF
    0.36
    NOT
    0.35
    Activations Density 0.740%

    No Known Activations