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. 6171
    Prev
    Next
    INDEX
    Explanations

    function definitions and calls related to setting parameters

    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
    ſelf
    -0.79
     Darum
    -0.79
     fread
    -0.79
     Stande
    -0.78
     NDEBUG
    -0.77
     оригіналу
    -0.77
     ARXIV
    -0.77
    OfBirth
    -0.76
     itſelf
    -0.76
    ftance
    -0.76
    POSITIVE LOGITS
    set
    1.28
     SET
    1.26
     set
    1.22
     Set
    1.21
    Set
    1.10
    SET
    1.07
     Sets
    1.04
     Seton
    0.97
     sets
    0.97
    sets
    0.96
    Activations Density 0.054%

    No Known Activations