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

    Neuronpedia

    APICircuit 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. 13-GEMMASCOPE-RES-16K
    6. 9452
    Prev
    Next
    INDEX
    Explanations

    sequences of underscores or gaps, indicating blank spaces or separations in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.58
    Gizmos
    -0.46
    Rupert
    -0.45
    ANSION
    -0.42
     Gracias
    -0.41
    onViewCreated
    -0.40
     putty
    -0.40
     twinkle
    -0.40
    Carrière
    -0.40
     pocit
    -0.39
    POSITIVE LOGITS
    mybatisplus
    1.19
     estekak
    0.83
     &___
    0.82
     незавершена
    0.81
    bkz
    0.81
    ########.
    0.78
    GraphicsUnit
    0.75
    AccessorTable
    0.74
     AssemblyTitle
    0.73
    rungsseite
    0.72
    Activations Density 0.110%

    No Known Activations