Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11610
    Prev
    Next
    INDEX
    Explanations

    references to team logos and branding related to sports teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     JpaRepository
    -0.54
     חיצוניים
    -0.53
     doInBackground
    -0.51
    ChildScrollView
    -0.50
     يتيمه
    -0.45
     متعلقه
    -0.45
     autorytatywna
    -0.44
     ChromeDriver
    -0.43
    ----</
    -0.42
     coaching
    -0.42
    POSITIVE LOGITS
     logo
    0.89
     Logo
    0.81
     logos
    0.79
    Logo
    0.77
    logo
    0.76
     logotipo
    0.67
    ロゴ
    0.64
     LOGO
    0.63
    logos
    0.62
     emblem
    0.62
    Activations Density 0.272%

    No Known Activations