© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1567
    Prev
    Next
    INDEX
    Explanations

    keywords related to education and learning interventions

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

    after articles/prepositions

    np_acts-logits-general · gemini-2.0-flash

    highly motivated champion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.41
    nps
    -0.28
     обра
    -0.27
    ͙
    -0.27
     发表于
    -0.27
    offsetof
    -0.26
     gewähr
    -0.26
    <bos>
    -0.26
     überw
    -0.25
    star
    -0.25
    POSITIVE LOGITS
    исленность
    0.64
    Autoritní
    0.60
    adaptiveStyles
    0.59
    fromnode
    0.57
     propOrder
    0.56
     المعيارى
    0.56
    usermodel
    0.55
    MeasureSpec
    0.54
     ویکی‌پدیا
    0.53
     насељу
    0.53
    Activations Density 1.054%

    No Known Activations