© 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
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 8160
    Prev
    Next
    INDEX
    Explanations

    references to entities and their significance in various contexts, particularly focusing on terms related to "the" and "a."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uaikan
    -0.42
     averaging
    -0.39
     práci
    -0.37
     smrti
    -0.35
    öglichkeiten
    -0.35
    lijck
    -0.35
     deepened
    -0.33
    harusnya
    -0.33
    Tarifs
    -0.32
     pracy
    -0.32
    POSITIVE LOGITS
    脚注の使い方
    0.71
     تضيفلها
    0.68
    tvguidetime
    0.61
    Diweddarwch
    0.52
     JADX
    0.50
     utafitiHapana
    0.50
     InputDecoration
    0.49
    multer
    0.49
    Bronnen
    0.48
    Tembelea
    0.48
    Activations Density 0.451%

    No Known Activations