© 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. 35-GEMMASCOPE-RES-16K
    11. 9526
    Prev
    Next
    INDEX
    Explanations

    technical terms and symbols used in programming and mathematics

    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
    TagNumber
    -0.51
    geslacht
    -0.50
     Marcello
    -0.50
    Dawson
    -0.49
     deafness
    -0.49
     Vaugh
    -0.48
     hornblende
    -0.47
     Jungkook
    -0.47
     chale
    -0.47
     marchand
    -0.46
    POSITIVE LOGITS
    Ciri
    0.69
    uri
    0.62
    hiri
    0.62
     Giri
    0.62
     Uribe
    0.60
     Aristi
    0.60
    iri
    0.60
    jiri
    0.59
    xi
    0.59
    siri
    0.58
    Activations Density 1.009%

    No Known Activations