© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 33-GEMMASCOPE-RES-16K
    11. 513
    Prev
    Next
    INDEX
    Explanations

    negations or phrases indicating lack of presence or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vooral
    -0.45
     faudrait
    -0.39
     slechts
    -0.37
     only
    -0.37
     ESPECIAL
    -0.36
     både
    -0.36
    sometimes
    -0.36
    almost
    -0.36
     především
    -0.36
    only
    -0.35
    POSITIVE LOGITS
     necessarily
    0.73
     any
    0.73
    有任何
    0.69
    任何
    0.66
     MainAxisSize
    0.65
     interfere
    0.65
     formally
    0.64
    enderror
    0.63
     kuiten
    0.63
     appreciably
    0.63
    Activations Density 1.077%

    No Known Activations