© 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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 434
    Prev
    Next
    INDEX
    Explanations

    comparative phrases that draw parallels between different concepts or situations

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

    Following "as" or related to simplification

    np_acts-logits-general · gemini-2.0-flash

    foreign languages

    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
    kháu
    -0.42
     resourceCulture
    -0.40
    isContained
    -0.38
     kapturem
    -0.38
     دریافت‌شده
    -0.37
    GRANTED
    -0.36
    PREPAR
    -0.36
     acu
    -0.35
     подготов
    -0.35
    mybatisplus
    -0.35
    POSITIVE LOGITS
     Italijanski
    0.58
     Winaray
    0.57
    TagMode
    0.50
    ⓧ
    0.44
     Италијани
    0.44
    Другие
    0.43
    ✭✭
    0.43
     précédentes
    0.42
    yasi
    0.42
     насељу
    0.42
    Activations Density 0.210%

    No Known Activations