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. 13-GEMMASCOPE-RES-16K
    6. 68
    Prev
    Next
    INDEX
    Explanations

    expressions related to frequency and quantity in various contexts

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

    instances of numerical sequences or statistics related to cases, occurrences, or quantities.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    مصادر
    -0.65
     bershka
    -0.64
     simplifié
    -0.63
     eds
    -0.63
     >=",
    -0.62
     Wicidata
    -0.61
    CROSSTALK
    -0.61
     Samos
    -0.60
     Jefus
    -0.59
    nanoTime
    -0.58
    POSITIVE LOGITS
     single
    0.68
     solitary
    0.65
     duy
    0.54
     lone
    0.53
     tunggal
    0.53
    AndEndTag
    0.51
    ViewFeatures
    0.50
     واحدة
    0.50
    migrationBuilder
    0.50
     pinulongan
    0.49
    Activations Density 0.585%

    No Known Activations