© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 38
    Prev
    Next
    INDEX
    Explanations

    occurrences of the prefix "un-"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StackNavigator
    -0.47
    fromnode
    -0.42
    ształ
    -0.40
    ついで
    -0.40
    extAlignment
    -0.39
    gique
    -0.39
    uated
    -0.37
     usine
    -0.37
    ivably
    -0.37
    тельству
    -0.37
    POSITIVE LOGITS
    un
    2.52
     Un
    1.99
    Un
    1.97
     un
    1.92
    UN
    1.80
     UN
    1.55
    ún
    1.01
     unf
    0.96
    unl
    0.90
    unna
    0.90
    Activations Density 0.166%

    No Known Activations