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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6810
    Prev
    Next
    INDEX
    Explanations

    code related to imports and component definitions in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     namorado
    -0.53
     FormBuilder
    -0.45
     appunt
    -0.44
     amizade
    -0.43
     noiva
    -0.43
     Tapia
    -0.43
     Leistungen
    -0.42
     rainha
    -0.40
     nationaux
    -0.40
    timbangan
    -0.40
    POSITIVE LOGITS
    oredCriteria
    1.00
     ویکی‌پدی
    0.98
     Italijanski
    0.85
     Roskov
    0.85
    IndentedString
    0.79
     Numerade
    0.77
    хьтан
    0.77
    WebVitals
    0.75
     lenker
    0.74
     незавершена
    0.74
    Activations Density 0.050%

    No Known Activations