© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 4049
    Prev
    Next
    INDEX
    Explanations

    instances of the word "not" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.81
     BoxFit
    -0.80
    PerformLayout
    -0.79
    Autoritní
    -0.79
     NSCoder
    -0.77
     Geſch
    -0.73
    RenderAtEndOf
    -0.72
     ſeine
    -0.71
     snippetHide
    -0.71
    adaptiveStyles
    -0.70
    POSITIVE LOGITS
    DoNot
    1.00
     cannot
    0.82
     not
    0.77
    Cannot
    0.72
     Cannot
    0.70
    cannot
    0.69
    Dont
    0.61
     Dont
    0.59
    t
    0.58
     dont
    0.58
    Activations Density 0.153%

    No Known Activations