© 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. 41-GEMMASCOPE-RES-16K
    11. 11327
    Prev
    Next
    INDEX
    Explanations

    the use of the word "well," indicating its association with positive evaluations or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -1.39
    Personendaten
    -1.13
     disambiguazione
    -1.13
    awtextra
    -1.11
     estekak
    -1.10
     Infórmanos
    -1.09
    uxxxx
    -1.07
     autorytatywna
    -1.06
    principalColumn
    -1.03
    httphttps
    -1.01
    POSITIVE LOGITS
     bodied
    0.31
     thereafter
    0.28
     suggestions
    0.23
    tothe
    0.20
     ass
    0.20
     other
    0.20
     ways
    0.20
     reasons
    0.19
     extensive
    0.19
     factors
    0.19
    Activations Density 0.261%

    No Known Activations