© 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. 31-GEMMASCOPE-RES-16K
    11. 1160
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'Na' and variations of it

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

    The neuron activates for text in languages other than English, particularly on prepositions like "na" and "sur" in Slavic and Romance languages.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    words or phrases that appear at the beginning of sentences or lines, particularly capitalized words that start new statements or sections.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ፩
    -0.44
    roto
    -0.41
     Conflict
    -0.41
    ersdorf
    -0.41
    umel
    -0.39
    âtel
    -0.39
    lul
    -0.39
     Collective
    -0.39
    illett
    -0.39
    rito
    -0.39
    POSITIVE LOGITS
     تضيفلها
    0.52
    ResponseWriter
    0.50
     henvisninger
    0.45
    pushFollow
    0.43
    providedIn
    0.43
    ंदीखरीदारी
    0.42
    IntoConstraints
    0.41
    addGap
    0.41
    Pranala
    0.40
     lenker
    0.40
    Activations Density 0.077%

    No Known Activations