© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1280
    Prev
    Next
    INDEX
    Explanations

    occurrences of the article "a" in various contexts

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

    Followed by adjectives/nouns

    np_acts-logits-general · gemini-2.0-flash

    a indefinite article

    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
     honneur
    -0.60
     læng
    -0.47
     vôtre
    -0.46
     voľ
    -0.46
     identité
    -0.45
     pretože
    -0.45
    queles
    -0.45
     intenção
    -0.45
     inscripción
    -0.44
     tarko
    -0.44
    POSITIVE LOGITS
     a
    1.36
     an
    0.98
     একটি
    0.84
    niſſe
    0.83
    einen
    0.82
    有个
    0.78
     ஒரு
    0.78
    ſſung
    0.77
     μια
    0.77
     queſto
    0.76
    Activations Density 1.229%

    No Known Activations