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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14310
    Prev
    Next
    INDEX
    Explanations

    mentions of nuclear weapons and international relations, particularly involving Russia

    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
    AppMethodBeat
    -0.55
    Jîn
    -0.53
     Autorisations
    -0.53
    rupal
    -0.50
    ollectionView
    -0.50
    BeginContext
    -0.49
    ArgumentParser
    -0.48
    ☚
    -0.47
    andExpect
    -0.47
     ROYAL
    -0.47
    POSITIVE LOGITS
     Arty
    0.32
     Zelensky
    0.31
    reportWebVitals
    0.30
    ########.
    0.30
    Graphic
    0.29
     quadro
    0.28
    kret
    0.28
    libft
    0.28
     lect
    0.28
     Silly
    0.27
    Activations Density 0.068%

    No Known Activations