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. 19-GEMMASCOPE-RES-16K
    6. 2257
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and operations related to products and limits in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    υσ
    -0.44
    arschu
    -0.43
     bambú
    -0.43
    epen
    -0.41
    Rounding
    -0.40
     käyt
    -0.40
    bado
    -0.39
     Accu
    -0.39
    verk
    -0.39
    symb
    -0.38
    POSITIVE LOGITS
    ViewFeatures
    0.95
     derivative
    0.84
    rungsseite
    0.81
    RenderAtEndOf
    0.80
     незавершена
    0.79
    principalTable
    0.78
     كومونز
    0.74
     derivatives
    0.74
     product
    0.73
     estekak
    0.72
    Activations Density 1.304%

    No Known Activations