© 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. 22-GEMMASCOPE-RES-16K
    11. 562
    Prev
    Next
    INDEX
    Explanations

    references to the audience or readers in a conversational or promotional context

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

    "You" followed by a modal verb

    np_acts-logits-general · gemini-2.0-flash

    you will

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    QtCore
    -0.49
     citado
    -0.49
    styleUrls
    -0.47
    alam
    -0.45
    illem
    -0.44
     planned
    -0.44
    ktor
    -0.43
    Cog
    -0.43
    slideUp
    -0.43
     다
    -0.42
    POSITIVE LOGITS
    ########.
    0.91
    +:+
    0.82
    Personendaten
    0.76
    Personensuche
    0.75
     مشين
    0.73
     وتسجيلات
    0.71
    abestanden
    0.69
     '\\;'
    0.69
    principalColumn
    0.68
     Вікіпе
    0.68
    Activations Density 0.083%

    No Known Activations