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. 20-GEMMASCOPE-RES-16K
    6. 16014
    Prev
    Next
    INDEX
    Explanations

    data structure and programming-related keywords and concepts in code.

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    pieces of code related to database queries and operations.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    key elements in code structures, particularly in web development and database queries.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     possibly
    -0.60
     potentially
    -0.55
    odacty
    -0.52
     fhould
    -0.52
     Há
    -0.51
     conceivably
    -0.51
    «,
    -0.51
    Searcher
    -0.51
     fich
    -0.51
     garcía
    -0.51
    POSITIVE LOGITS
     propOrder
    0.83
    ValueStyle
    0.76
    MigrationBuilder
    0.75
     upto
    0.74
    userdetails
    0.73
     resourceCulture
    0.71
    +#+#
    0.70
    ьаж
    0.68
     saper
    0.65
    MessageOf
    0.65
    Activations Density 0.121%

    No Known Activations