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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 10777
    Prev
    Next
    INDEX
    Explanations

    references to used goods and their conditions, particularly in sales contexts

    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
    tiness
    -0.63
    hadiran
    -0.62
     Efq
    -0.59
     levure
    -0.58
    ้งาน
    -0.58
    diali
    -0.57
    Síguenos
    -0.56
     كومونز
    -0.56
     againſt
    -0.55
     acrylique
    -0.55
    POSITIVE LOGITS
    ebay
    0.64
     thrift
    0.60
    webElementGuid
    0.58
     condition
    0.58
     secondhand
    0.57
    condition
    0.57
    RegressionTest
    0.55
     vintage
    0.54
    Condition
    0.52
    中古
    0.52
    Activations Density 0.227%

    No Known Activations