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. 2-GEMMASCOPE-RES-16K
    6. 15129
    Prev
    Next
    INDEX
    Explanations

    positive expressions and recommendations about services and products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nonUne
    -0.77
    matchCondition
    -0.67
    WithIOException
    -0.64
    таратура
    -0.57
     مرئيه
    -0.55
    sizeCache
    -0.54
    isbol
    -0.53
    PROG
    -0.52
     nakalista
    -0.52
    ButterKnife
    -0.52
    POSITIVE LOGITS
    UnitTesting
    0.70
     Pliny
    0.66
     beware
    0.65
     Monfieur
    0.58
    ️
    0.57
     Brahmin
    0.57
     Consiglio
    0.56
    RunWith
    0.55
     Athenians
    0.55
     honte
    0.55
    Activations Density 0.397%

    No Known Activations