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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 4600
    Prev
    Next
    INDEX
    Explanations

    time-related information and event schedules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    期刊论文
    -0.61
    protoimpl
    -0.54
    tamol
    -0.54
     leksikon
    -0.53
    はじめに
    -0.52
    endsection
    -0.51
    (\%)
    -0.51
    PARAMETERS
    -0.51
    hoven
    -0.50
    ZV
    -0.50
    POSITIVE LOGITS
    Slf
    0.67
     NSCoder
    0.65
    Lähteet
    0.63
    ViewFeatures
    0.63
    Kaynakça
    0.58
    liferay
    0.57
    bootstrapcdn
    0.57
     uova
    0.57
     LoggerFactory
    0.56
     يتيمه
    0.55
    Activations Density 0.066%

    No Known Activations