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. 10902
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology, specifically issues and solutions in programming or software development

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

    Beginning of sentences or clauses

    np_acts-logits-general · gemini-2.0-flash

    assuming perfect conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     оригіналу
    -0.59
    nteral
    -0.57
    chium
    -0.56
     बजाय
    -0.52
     pinulongan
    -0.50
    #+#
    -0.48
    ########.
    -0.48
    ausch
    -0.47
     disponibles
    -0.47
     Vikipedi
    -0.47
    POSITIVE LOGITS
     everything
    2.44
    everything
    2.24
     Everything
    2.13
    Everything
    2.11
     tudo
    1.64
     alles
    1.61
     EVERYTHING
    1.51
     всичко
    1.47
     totul
    1.46
     wszystko
    1.45
    Activations Density 0.251%

    No Known Activations