© 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. 305
    Prev
    Next
    INDEX
    Explanations

    references to teaching and related educational concepts

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

    "teaching" followed by certain words

    np_acts-logits-general · gemini-2.0-flash

    teaching methods

    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
    principalTable
    -0.78
     للاسماء
    -0.72
    WebElementEntity
    -0.72
    zzleHttp
    -0.71
    rungsseite
    -0.67
     Hütte
    -0.67
    ImageContext
    -0.66
     noqa
    -0.65
    IBarButtonItem
    -0.64
    nits
    -0.63
    POSITIVE LOGITS
    teaching
    0.64
    teach
    0.62
     teach
    0.61
     teaches
    0.60
     teaching
    0.57
     TEACH
    0.57
     teachers
    0.57
    Teaching
    0.56
    teachers
    0.56
    傅
    0.53
    Activations Density 0.054%

    No Known Activations