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. 21-GEMMASCOPE-RES-16K
    6. 321
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the character "い" and similar characters visually or phonetically at a high frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    جراء
    -0.50
    いたら
    -0.49
     Survive
    -0.49
    îtra
    -0.48
    ULING
    -0.48
    خرى
    -0.48
     bao
    -0.47
     fick
    -0.47
    ANNELS
    -0.46
     Raff
    -0.46
    POSITIVE LOGITS
     Wikimedijinoj
    0.74
     GenerationType
    0.68
     Poitiers
    0.67
     JpaRepository
    0.66
     viewDidLoad
    0.60
    脚注の使い方
    0.60
    onViewCreated
    0.59
    anças
    0.59
     Allegretto
    0.59
     ejus
    0.59
    Activations Density 0.039%

    No Known Activations