Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 1875
    Prev
    Next
    INDEX
    Explanations

    programming language syntax elements and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -1.12
    ⓧ
    -0.94
    StructEnd
    -0.93
     مشين
    -0.92
     Efq
    -0.92
    RectangleBorder
    -0.90
     JpaRepository
    -0.87
    ftagPool
    -0.86
    XmlAccessType
    -0.86
    KommentareTeilen
    -0.85
    POSITIVE LOGITS
    ISODE
    0.53
     co
    0.52
     public
    0.49
    elock
    0.48
    uxxxx
    0.47
    awt
    0.47
     độ
    0.47
     head
    0.47
    identes
    0.46
    QFont
    0.46
    Activations Density 0.014%

    No Known Activations