© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 83392
    Prev
    Next
    INDEX
    Explanations

    instances of the word "shouldn't" in negative contexts

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

    shouldn't followed by verbs

    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
    enumi
    -0.52
    dflare
    -0.46
     eigener
    -0.46
    ymce
    -0.43
     Vries
    -0.43
    ValueGenerated
    -0.42
     Palabra
    -0.42
    nonatomic
    -0.41
     juta
    -0.40
    gamesh
    -0.40
    POSITIVE LOGITS
     shouldn
    1.97
    should
    1.59
     Shouldn
    1.55
     should
    1.55
    Shouldn
    1.47
    Should
    1.47
     shouldnt
    1.45
     Should
    1.42
     ſhould
    1.40
     SHOULD
    1.34
    Activations Density 0.001%

    No Known Activations