© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 82204
    Prev
    Next
    INDEX
    Explanations

    phrases indicating inability or negation, particularly involving the word "not."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    could not + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Références
    -0.39
     inicios
    -0.39
    tênis
    -0.39
     gonna
    -0.39
    belongs
    -0.38
    łóż
    -0.37
    dealloc
    -0.37
    枉
    -0.37
    subpackage
    -0.36
     harms
    -0.36
    POSITIVE LOGITS
     could
    0.73
     Could
    0.69
    Could
    0.67
     couldnt
    0.64
    could
    0.64
     Couldn
    0.62
     kunde
    0.58
     couldn
    0.57
    Couldn
    0.56
     COULD
    0.56
    Activations Density 0.015%

    No Known Activations