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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 5701
    Prev
    Next
    INDEX
    Explanations

    terms related to kinetic theory and the study of energy dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kitchen
    -0.72
     kinetic
    -0.64
    kitchen
    -0.61
     keyword
    -0.57
    keyword
    -0.56
    Kitchen
    -0.56
     keywords
    -0.54
    kinetic
    -0.54
    keyboard
    -0.53
    Keyword
    -0.53
    POSITIVE LOGITS
     pneumoniae
    0.60
     vực
    0.55
     Lumpur
    0.46
    StructEnd
    0.44
    foglio
    0.40
     Permanente
    0.38
    wurst
    0.38
    ("")]
    0.38
     XK
    0.37
     inductance
    0.37
    Activations Density 0.619%

    No Known Activations