© 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. 13086
    Prev
    Next
    INDEX
    Explanations

    variations of the root word "fraction" and its related forms

    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
    AndEndTag
    -0.47
    SSM
    -0.45
     myſelf
    -0.45
    Jîn
    -0.45
    verwijspagina
    -0.45
     للمعارف
    -0.44
    InSection
    -0.43
    extAlignment
    -0.43
    OpenHelper
    -0.43
    reportWebVitals
    -0.43
    POSITIVE LOGITS
     Fra
    0.83
    Fra
    0.79
     Frag
    0.73
     frag
    0.72
     Fragment
    0.68
     fra
    0.68
    fra
    0.66
     Fraser
    0.65
    Frag
    0.65
    fragment
    0.63
    Activations Density 0.169%

    No Known Activations