© 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. 11-GEMMASCOPE-RES-16K
    11. 9961
    Prev
    Next
    INDEX
    Explanations

    terms related to thermodynamics and energy systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.77
     Italijanski
    -0.72
     snippetHide
    -0.71
     NSCoder
    -0.70
    UserScript
    -0.70
    <pad>
    -0.69
    <unused43>
    -0.68
    <unused74>
    -0.68
    <unused41>
    -0.68
    <unused28>
    -0.68
    POSITIVE LOGITS
     LEG
    0.32
     between
    0.25
    ,
    0.24
     border
    0.24
     effects
    0.23
     more
    0.23
     expansion
    0.23
     of
    0.23
     across
    0.23
     claros
    0.23
    Activations Density 0.751%

    No Known Activations