© 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. 14494
    Prev
    Next
    INDEX
    Explanations

    programming-related terminology and syntax

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

    personal pronouns, especially clitic/object and first/second person forms across multiple languages.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    tokens in non-English languages, particularly Slavic languages (Croatian, Serbian, etc.) and Romance languages (French, Indonesian/Malay).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    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
    wahati
    -0.47
    illoma
    -0.43
    ttemberg
    -0.43
    よくある
    -0.42
    sitive
    -0.42
    PreferredItem
    -0.42
     Prairie
    -0.41
    länd
    -0.40
    umenical
    -0.40
    FromArgb
    -0.39
    POSITIVE LOGITS
     ellos
    0.59
    Them
    0.59
     juos
    0.56
     noastre
    0.56
    เอง
    0.56
     beliau
    0.56
     sendiri
    0.55
     berdua
    0.55
     Ellos
    0.55
    ándolos
    0.54
    Activations Density 0.050%

    No Known Activations