© 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. 20-GEMMASCOPE-RES-131K
    11. 44887
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "in" and variations of the phrase "not in"

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

    set membership or exclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -0.72
     Jefus
    -0.62
     faſt
    -0.61
     AppCompatTheme
    -0.60
     ſche
    -0.60
     queſta
    -0.60
     betweenstory
    -0.59
    évaluateur
    -0.59
    AddTagHelper
    -0.59
     Anſ
    -0.57
    POSITIVE LOGITS
     among
    0.40
     disponibilité
    0.37
    import
    0.36
    GEBURTSDATUM
    0.36
    AutoresizingMask
    0.34
     existing
    0.34
     list
    0.33
    入
    0.32
    catchError
    0.32
     deep
    0.31
    Activations Density 0.010%

    No Known Activations