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. 667
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly related to author credits or copyright information

    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
     Италијани
    -0.84
     Italijanski
    -0.64
     հղումներ
    -0.59
     betweenstory
    -0.59
     Мексичка
    -0.52
    adaptiveStyles
    -0.52
    Aholisi
    -0.51
     ModelRenderer
    -0.51
     墊
    -0.50
    oa̍t
    -0.50
    POSITIVE LOGITS
     '\\;'
    0.43
    principalColumn
    0.36
     perspiration
    0.31
     MULTIPLE
    0.30
     الض
    0.29
     ?>">
    0.28
    (@"
    0.28
     richi
    0.28
     berle
    0.27
    الحياه
    0.27
    Activations Density 0.345%

    No Known Activations