Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-GEMMASCOPE-RES-16K
    6. 8649
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to study design and data collection methodology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.89
    TagMode
    -0.85
     متعلقه
    -0.81
    rungsseite
    -0.74
    verwijspagina
    -0.74
    Personensuche
    -0.72
     للاسماء
    -0.71
    出版年
    -0.70
    +#+#
    -0.70
     EconPapers
    -0.63
    POSITIVE LOGITS
    toMatchSnapshot
    0.67
    amarin
    0.50
    unconfirmed
    0.49
    atonic
    0.49
    且
    0.47
    GetKeyDown
    0.47
    bParam
    0.47
    asable
    0.46
    ByDefault
    0.46
    度的
    0.46
    Activations Density 0.766%

    No Known Activations