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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 10117
    Prev
    Next
    INDEX
    Explanations

    keywords and acronyms related to healthcare and medical studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دانشنامهٔ
    -0.85
    出版年
    -0.81
     تانيه
    -0.78
     հղումներ
    -0.76
    يميديا
    -0.72
    Jeografia
    -0.70
    OptionsMenu
    -0.70
    mybatisplus
    -0.70
    ніципа
    -0.68
     дописавши
    -0.68
    POSITIVE LOGITS
    s
    0.85
    aaS
    0.61
     aandacht
    0.55
     stappen
    0.55
    värr
    0.54
     verksamhet
    0.54
     gezet
    0.53
     sauvages
    0.52
     bonheur
    0.52
    świad
    0.51
    Activations Density 1.240%

    No Known Activations