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. 16-GEMMASCOPE-RES-16K
    6. 2935
    Prev
    Next
    INDEX
    Explanations

    contractions and the word "be" in various forms, indicating a focus on verbs and their usages

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

    Third-person singular pronouns

    np_acts-logits-general · gemini-2.0-flash

    He or she is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sirva
    -0.46
     disambiguazione
    -0.45
     række
    -0.43
     rekke
    -0.41
     équi
    -0.41
     vė
    -0.41
     lò
    -0.40
     applicability
    -0.40
     variés
    -0.40
    Comté
    -0.39
    POSITIVE LOGITS
    ModelSerializer
    0.79
    Abitanti
    0.75
     married
    0.72
    openzeppelin
    0.72
     MainAxisSize
    0.69
     afraid
    0.69
     famous
    0.66
     obsessed
    0.66
    Datuak
    0.66
     kidding
    0.66
    Activations Density 0.359%

    No Known Activations