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. 2681
    Prev
    Next
    INDEX
    Explanations

    mention of notable filmmakers and their contributions to cinema

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

    Third-person singular present tense verbs

    np_acts-logits-general · gemini-2.0-flash

    possessive pronouns and work output

    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
     volunteers
    -0.51
     officers
    -0.49
    Drum
    -0.48
     Poem
    -0.47
     enforceable
    -0.47
    文物
    -0.46
    Drums
    -0.46
     poem
    -0.46
    veste
    -0.46
    Volunteers
    -0.46
    POSITIVE LOGITS
     prolific
    0.90
    出版年
    0.81
    verwijspagina
    0.80
     productions
    0.79
    ագրություններ
    0.78
     carriera
    0.75
     collaborations
    0.74
     output
    0.72
     oeuvre
    0.72
    Portail
    0.71
    Activations Density 0.279%

    No Known Activations