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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 438
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to proteins and enzymes, particularly those involved in inflammation and biological processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jangkau
    -0.23
     @"/
    -0.22
     (
    -0.19
     \
    -0.19
     a
    -0.19
     is
    -0.19
     нужны
    -0.19
     ausges
    -0.19
     as
    -0.18
     copy
    -0.18
    POSITIVE LOGITS
     betweenstory
    0.92
    RegressionTest
    0.91
     jScrollPane
    0.76
    出版年
    0.76
     Rigidbody
    0.75
    majánló
    0.74
    <unused8>
    0.74
     fashiola
    0.74
    <unused16>
    0.73
    <unused42>
    0.73
    Activations Density 1.880%

    No Known Activations