© 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. 3-GEMMASCOPE-RES-16K
    6. 10617
    Prev
    Next
    INDEX
    Explanations

    HTML or XML tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theſe
    -1.34
     المعيارى
    -1.32
     Efq
    -1.27
     يتيمه
    -1.22
     disambiguazione
    -1.17
     itſelf
    -1.13
    ItemBackground
    -1.08
    PreferredItem
    -1.06
     JpaRepository
    -1.06
    mybatisplus
    -1.05
    POSITIVE LOGITS
    <
    1.08
    ><
    0.95
    .
    0.82
    "><
    0.78
    <eos>
    0.75
     <
    0.70
    ?
    0.69
    [
    0.68
     
    0.67
     a
    0.67
    Activations Density 0.100%

    No Known Activations