© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 5777
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical symbols and quantities in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Foer
    -0.55
    bip
    -0.54
     Earle
    -0.51
    ついで
    -0.50
    Ern
    -0.49
    versiti
    -0.49
    ("")]
    -0.49
     Joc
    -0.49
    '],
    -0.47
     Earl
    -0.47
    POSITIVE LOGITS
    Omega
    3.49
     Omega
    2.61
    Ω
    2.25
     Ω
    2.23
     omega
    2.04
    Ω
    1.71
    omega
    1.49
    
    1.27
    MEGA
    1.01
    ω
    0.96
    Activations Density 0.123%

    No Known Activations