© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12451
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" and other auxiliary verbs in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     medes
    -0.52
    basedir
    -0.45
    Vag
    -0.44
    daging
    -0.44
    moiselle
    -0.43
    xPos
    -0.42
    Eli
    -0.41
     casal
    -0.40
    raisemb
    -0.40
    IVEREF
    -0.40
    POSITIVE LOGITS
     adalah
    0.79
     è
    0.79
     είναι
    0.78
     ist
    0.73
     là
    0.70
    ίναι
    0.70
     är
    0.69
     is
    0.66
     é
    0.66
     является
    0.66
    Activations Density 0.093%

    No Known Activations