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. 5-GEMMASCOPE-RES-16K
    6. 13409
    Prev
    Next
    INDEX
    Explanations

    references to programming libraries and file attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.75
    arial
    -0.73
    ^(@)
    -0.73
    __':
    -0.70
    äischen
    -0.69
    .$_
    -0.68
    comings
    -0.67
     noqa
    -0.67
    ünst
    -0.67
    bibfield
    -0.64
    POSITIVE LOGITS
    AndEndTag
    0.94
    stereotype
    0.90
    eqn
    0.88
    arXiv
    0.87
    GraphicsUnit
    0.77
    ByteString
    0.74
    Kaynakça
    0.69
    GroupLayout
    0.68
    UIControlState
    0.65
    fjspx
    0.64
    Activations Density 0.007%

    No Known Activations