© 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. 8994
    Prev
    Next
    INDEX
    Explanations

    negative prefixes indicating negation or absence

    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
    льзя
    -0.84
    смотря
    -0.80
    ได้
    -0.75
    обходимо
    -0.73
    має
    -0.71
    reated
    -0.70
    zbęd
    -0.66
    ют
    -0.66
    возможно
    -0.64
    够
    -0.64
    POSITIVE LOGITS
    ziasztok
    0.37
    thenReturn
    0.36
     élevées
    0.34
    makeText
    0.33
    nesc
    0.32
     cảnh
    0.31
    thâu
    0.31
    likle
    0.30
     Families
    0.30
     laiton
    0.30
    Activations Density 0.174%

    No Known Activations