© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15808
    Prev
    Next
    INDEX
    Explanations

    references to education-related topics and the experiences of educators

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

    teachers or teaching

    np_acts-logits-general · gemini-2.0-flash

    teachers and educators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    epresidente
    -0.47
    ญา
    -0.45
    tamo
    -0.43
    perusahaan
    -0.42
    spo
    -0.41
    लय
    -0.41
     spo
    -0.41
     Auss
    -0.41
    civi
    -0.40
    /*:
    -0.40
    POSITIVE LOGITS
     teacher
    1.42
     teachers
    1.29
     Teacher
    1.28
     Teachers
    1.21
    teacher
    1.21
     pedagogical
    1.18
    Teacher
    1.16
     educators
    1.13
    Teachers
    1.11
    TEACHER
    1.11
    Activations Density 0.319%

    No Known Activations