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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 15036
    Prev
    Next
    INDEX
    Explanations

    content related to educational resources and their appropriateness for different grade levels

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

    grade levels (elementary, middle, high)

    np_acts-logits-general · gemini-2.0-flash

    school grades and levels

    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
    +#+#
    -0.80
    PreferredItem
    -0.68
     ***!
    -0.61
    出版年
    -0.57
     zä
    -0.57
     createSlice
    -0.56
    Jeografia
    -0.54
    ThroughAttribute
    -0.54
    CPtr
    -0.53
    ogyn
    -0.53
    POSITIVE LOGITS
     elementary
    1.92
     grade
    1.80
     primary
    1.68
     Elementary
    1.64
    elementary
    1.62
     middle
    1.60
    Elementary
    1.59
     Grade
    1.58
     Primary
    1.55
    Primary
    1.50
    Activations Density 0.339%

    No Known Activations