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. 12935
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting elements in code snippets

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

    Comes before context, boot, http, nn, nature, contrib

    np_acts-logits-general · gemini-2.0-flash

    . by ((& an insulating

    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
    enciaga
    -0.75
    writerow
    -0.71
    +:+
    -0.68
    Geplaatst
    -0.68
    elemField
    -0.64
    NOPQRST
    -0.63
    Dona
    -0.61
    DIPSETTING
    -0.61
    WithMany
    -0.60
    IUrlHelper
    -0.59
    POSITIVE LOGITS
    beans
    0.77
     Falcons
    0.75
    بوابة
    0.72
    stereotype
    0.71
     MonoBehaviour
    0.60
     StatefulWidget
    0.58
    dao
    0.58
    ḵ
    0.57
    RectangleBorder
    0.57
     PPI
    0.57
    Activations Density 0.003%

    No Known Activations