© 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. 15362
    Prev
    Next
    INDEX
    Explanations

    phrases related to accuracy and performance in a system or process

    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
     الاطلاع
    -0.31
    自己是
    -0.31
    חה
    -0.31
    Herzliche
    -0.29
    født
    -0.26
    elola
    -0.26
    Читайте
    -0.25
    Related
    -0.25
    ảng
    -0.24
    iske
    -0.24
    POSITIVE LOGITS
     desired
    2.05
     planned
    1.95
     promised
    1.87
     intended
    1.82
     predicted
    1.81
    desired
    1.81
     requested
    1.77
    planned
    1.70
     anticipated
    1.70
     expected
    1.70
    Activations Density 1.261%

    No Known Activations