© 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. 2-GEMMASCOPE-RES-16K
    11. 11651
    Prev
    Next
    INDEX
    Explanations

    negative contractions and the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Espèce
    -0.53
     الرياضيه
    -0.51
     linkovi
    -0.48
    StoryboardSegue
    -0.46
    cookieParser
    -0.46
    +#+#
    -0.43
     ModelRenderer
    -0.43
    eapon
    -0.43
     snippetHide
    -0.43
    lesias
    -0.42
    POSITIVE LOGITS
     cannot
    1.54
     Cannot
    1.48
    cannot
    1.45
    Cannot
    1.44
     cant
    1.39
    Cant
    1.29
    cant
    1.23
     Cant
    1.22
     CANNOT
    1.21
     CANT
    1.11
    Activations Density 0.176%

    No Known Activations