© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 11257
    Prev
    Next
    INDEX
    Explanations

    terms related to germination and the effects of specific amino acids

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.63
    RegressionTest
    -0.57
     contigo
    -0.50
    يكب
    -0.47
     CHtml
    -0.47
    UnusedPrivate
    -0.47
     незавершена
    -0.46
    AddTagHelper
    -0.45
     Italijanski
    -0.45
     disambiguazione
    -0.44
    POSITIVE LOGITS
     amino
    1.12
     Amino
    0.94
    amino
    0.85
    Amino
    0.84
     glycine
    0.72
     alan
    0.72
     lysine
    0.67
    氨
    0.64
     arginine
    0.63
     amin
    0.63
    Activations Density 1.044%

    No Known Activations