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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14282
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their formatting in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новништво
    -0.50
     alimentaria
    -0.43
    Portale
    -0.42
     betweenstory
    -0.42
     megfelelő
    -0.41
    tanleria
    -0.40
    astify
    -0.40
     població
    -0.40
     Manners
    -0.39
    rrggbb
    -0.39
    POSITIVE LOGITS
     }{@
    0.63
     nakalista
    0.58
     propOrder
    0.52
    fjspx
    0.51
    حوالہ
    0.50
     disambiguazione
    0.49
    <!--[
    0.49
     चीज़ों
    0.47
     bad
    0.46
    Parcelize
    0.45
    Activations Density 2.489%

    No Known Activations