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. 3815
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and their relationships, particularly involving squares and proportions

    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
     facie
    -0.53
    ghest
    -0.53
    mistic
    -0.52
     समीक्षक
    -0.49
    چسب
    -0.49
    GHIJKLM
    -0.49
    untura
    -0.48
    こそ
    -0.47
    ėmis
    -0.47
    спеди
    -0.47
    POSITIVE LOGITS
    ⓧ
    0.75
    cmath
    0.71
     JpaRepository
    0.62
    Réponse
    0.57
     &___
    0.57
    }\]
    0.55
     bezeichneter
    0.53
    jamas
    0.53
    økt
    0.53
    webElementXpaths
    0.51
    Activations Density 1.604%

    No Known Activations