Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104999
    Prev
    Next
    INDEX
    Explanations

    references to parliamentary procedures and debates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Билгалдахарш
    -0.66
     ویکی‌پدی
    -0.66
    Datuak
    -0.63
    Personendaten
    -0.63
     nonUne
    -0.63
    Хьажоргаш
    -0.60
    GEBURTSDATUM
    -0.57
     المعيارى
    -0.57
    MessageOf
    -0.57
    transQ
    -0.57
    POSITIVE LOGITS
    getMenuInflater
    0.40
     MonoBehaviour
    0.39
    ront
    0.38
    withOpacity
    0.36
    ">//
    0.36
    GoogleApiClient
    0.35
    StrictMode
    0.35
    complexType
    0.33
    OnInit
    0.33
    AutoresizingMask
    0.33
    Activations Density 0.025%

    No Known Activations