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-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 11080
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their interactions, particularly involving carbon dioxide

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    @[+][
    -0.53
    bigsqcup
    -0.49
    omeness
    -0.49
    ZIE
    -0.47
     turno
    -0.47
    Grounded
    -0.47
    bigcup
    -0.47
    jalá
    -0.46
    OfMonth
    -0.45
     OnInit
    -0.45
    POSITIVE LOGITS
     dioxide
    1.18
     Dioxide
    1.15
     gases
    0.93
    出版年
    0.87
     gas
    0.86
     smoke
    0.79
     monoxide
    0.78
     gaseous
    0.75
     Gases
    0.74
     gás
    0.74
    Activations Density 0.592%

    No Known Activations