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. 8-GEMMASCOPE-RES-16K
    6. 3810
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation, often related to equations or formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyVersion
    -0.86
    enumi
    -0.84
    waitKey
    -0.81
     بيها
    -0.78
    elemField
    -0.76
     Waray
    -0.74
     незавершена
    -0.74
    şekkür
    -0.74
    twimg
    -0.73
    Concurrency
    -0.73
    POSITIVE LOGITS
    1
    0.92
    IBinder
    0.66
     ১
    0.60
    ZoneId
    0.59
    ONE
    0.57
    ViewFeatures
    0.56
     ONE
    0.55
     singular
    0.54
    typeId
    0.54
     jit
    0.54
    Activations Density 0.777%

    No Known Activations