© 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. 10611
    Prev
    Next
    INDEX
    Explanations

    terms related to collaborative research efforts

    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
    ########.
    -0.43
    nóstico
    -0.42
     näh
    -0.41
    exitRule
    -0.40
     كومونز
    -0.40
     soldadura
    -0.40
     dévelo
    -0.40
    BeginInit
    -0.38
    terer
    -0.38
     equipada
    -0.37
    POSITIVE LOGITS
     journal
    1.29
     journals
    1.17
     Journal
    1.06
     peer
    1.05
     Journals
    0.97
    journal
    0.97
    Journal
    0.95
    journals
    0.93
     JOURNAL
    0.91
     papers
    0.90
    Activations Density 2.785%

    No Known Activations