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. 1693
    Prev
    Next
    INDEX
    Explanations

    references to organized data structures or systems, particularly in programming and legal contexts

    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
    Hochspringen
    -0.45
     Văn
    -0.44
     off
    -0.43
    <u>
    -0.43
     Dar
    -0.43
     good
    -0.41
    okes
    -0.41
     يتيمه
    -0.40
     it
    -0.40
    +#+#
    -0.39
    POSITIVE LOGITS
     propOrder
    0.78
     تكبرها
    0.78
    RenderAtEndOf
    0.75
     ExecuteAsync
    0.75
     initComponents
    0.72
     poffe
    0.67
     ")");
    0.67
     poffible
    0.67
     useDispatch
    0.66
     ſtate
    0.66
    Activations Density 0.981%

    No Known Activations