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. 0-GEMMASCOPE-RES-16K
    6. 429
    Prev
    Next
    INDEX
    Explanations

    terms related to keyboards and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.56
    PageRoute
    -0.52
    πω
    -0.51
    DJANGO
    -0.51
    <?
    -0.50
     Acti
    -0.48
    िखित
    -0.46
     Koh
    -0.46
     koh
    -0.46
     viſ
    -0.45
    POSITIVE LOGITS
    xase
    0.74
    writeFieldEnd
    0.74
     pinulongan
    0.73
     TType
    0.70
     sheep
    0.69
     InputDecoration
    0.69
    rasil
    0.69
    complexContent
    0.68
     Mary
    0.67
    sheep
    0.66
    Activations Density 0.090%

    No Known Activations