© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 10943
    Prev
    Next
    INDEX
    Explanations

    verbs indicating states of being or actions related to relationships and commitments

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

    Auxiliary verbs (is, was, are, etc.)

    np_acts-logits-general · gemini-2.0-flash

    forms of "to be" followed by descriptive word/phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    انيف
    -0.68
     ""],
    -0.60
    Демографія
    -0.57
    Koordinaten
    -0.55
     capping
    -0.52
    iocene
    -0.52
     विश्वसनीयता
    -0.52
    Numerology
    -0.49
     seniority
    -0.49
    elfde
    -0.48
    POSITIVE LOGITS
    IVEREF
    0.61
     yii
    0.60
     تضيفلها
    0.59
     capaces
    0.57
     esternos
    0.55
     nakalista
    0.55
     Wiktionnaire
    0.54
     úspě
    0.53
    PhysRevLett
    0.52
     ujednoznacz
    0.52
    Activations Density 0.285%

    No Known Activations