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. 11-GEMMASCOPE-RES-16K
    6. 5866
    Prev
    Next
    INDEX
    Explanations

    names of persons and institutions along with associated entities in a research context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    JspWriter
    -0.47
    rshire
    -0.44
     Вікі
    -0.43
     obicei
    -0.42
    lam
    -0.41
    daj
    -0.41
    insegna
    -0.40
     cờ
    -0.40
    pected
    -0.40
    δου
    -0.40
    POSITIVE LOGITS
    AutoField
    0.91
    :✨
    0.79
    RenderAtEndOf
    0.74
     مشين
    0.73
    AntiForgeryToken
    0.70
    ResumeLayout
    0.68
    WebpackPlugin
    0.67
    CloseOperation
    0.65
    __*/
    0.64
    省市镇
    0.64
    Activations Density 0.211%

    No Known Activations