Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 52926
    Prev
    Next
    INDEX
    Explanations

    instances of the word "teach" and its variations related to education or instructing others

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

    imparting knowledge

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    isler
    -0.50
    ----------------
    -0.50
    1
    -0.45
    GPL
    -0.44
     hảo
    -0.44
    del
    -0.44
    ker
    -0.43
    íž
    -0.43
    a
    -0.43
    X
    -0.43
    POSITIVE LOGITS
     taught
    1.26
     Taught
    1.23
     teaches
    1.19
     teach
    1.16
    taught
    1.16
    teach
    1.12
     Teach
    1.07
    Teach
    1.04
     lessons
    1.01
     TEACH
    0.96
    Activations Density 0.035%

    No Known Activations