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. 5-GEMMASCOPE-RES-16K
    6. 2751
    Prev
    Next
    INDEX
    Explanations

    references to color codes or color attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.81
    GetEnumerator
    -0.77
     Réponses
    -0.75
     simplifié
    -0.75
    
    -0.73
     intégrée
    -0.72
    JspWriter
    -0.72
     récomp
    -0.72
     XCTest
    -0.71
    NoSuchAlgorithm
    -0.70
    POSITIVE LOGITS
     col
    2.27
     Col
    2.22
    col
    2.17
    Col
    2.15
     COL
    1.96
    COL
    1.75
     COLL
    1.53
     cols
    1.45
    Cols
    1.41
     Kol
    1.40
    Activations Density 0.062%

    No Known Activations