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. 20-GEMMASCOPE-RES-16K
    6. 12160
    Prev
    Next
    INDEX
    Explanations

    code references related to date parsing and formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.56
    الحياه
    -0.56
    ado
    -0.53
     للاسماء
    -0.52
    HtmlAttribute
    -0.52
    جغرافيا
    -0.51
    aarrggbb
    -0.51
    קישורים
    -0.50
    DebuggerNonUser
    -0.50
    ValueStyle
    -0.48
    POSITIVE LOGITS
     vectorielle
    0.65
    BASEPATH
    0.64
     Địa
    0.59
    UAGES
    0.59
     polaire
    0.58
     poffible
    0.56
     facilité
    0.56
     énergé
    0.56
     Malabar
    0.56
    Hentet
    0.55
    Activations Density 0.159%

    No Known Activations