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. 16078
    Prev
    Next
    INDEX
    Explanations

    words or phrases associated with costs and expenses

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

    followed by "of" or "the"

    np_acts-logits-general · gemini-2.0-flash

    self-referential words and pronouns

    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
    WebMethod
    -0.78
    findpost
    -0.69
     تضيفلها
    -0.65
    AddHtmlAttribute
    -0.65
     pinulongan
    -0.59
    contentLoaded
    -0.56
    interopRequire
    -0.56
    featureID
    -0.55
    WriteBarrier
    -0.51
     BytesLike
    -0.50
    POSITIVE LOGITS
     сам
    0.71
     själva
    0.70
     сами
    0.69
     selve
    0.68
     сама
    0.68
     themselves
    0.67
    Сам
    0.66
     самой
    0.66
     самого
    0.65
    Portail
    0.62
    Activations Density 0.565%

    No Known Activations