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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 58553
    Prev
    Next
    INDEX
    Explanations

    references to teaching and educational concepts

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

    teach mathematics or English

    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
    RRect
    -0.46
     Kraus
    -0.44
     Raton
    -0.42
     Margo
    -0.41
    ondes
    -0.41
     Goldman
    -0.40
    lgari
    -0.39
     Belvedere
    -0.39
    oro
    -0.39
     Swanson
    -0.39
    POSITIVE LOGITS
     teach
    1.13
    Teach
    1.12
     Teach
    1.02
    taught
    1.01
    teach
    1.00
     Taught
    1.00
     TEACH
    0.99
     teaches
    0.98
    teaching
    0.95
     Teaching
    0.93
    Activations Density 0.008%

    No Known Activations