© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 16367
    Prev
    Next
    INDEX
    Explanations

    references to mathematical constructs or parameters related to energy in physical theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rospy
    -0.70
     Jock
    -0.68
     Gok
    -0.63
     Cork
    -0.63
    cork
    -0.61
    Cork
    -0.61
    WebElementEntity
    -0.60
    ьаж
    -0.60
    Lähteet
    -0.59
    windowFixed
    -0.58
    POSITIVE LOGITS
    Delta
    2.88
     Delta
    2.56
     Δ
    2.16
    DELTA
    2.02
    Δ
    2.01
     DELTA
    1.93
     ∆
    1.76
    ∆
    1.76
     delta
    1.66
    △
    1.55
    Activations Density 0.088%

    No Known Activations