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. 21-GEMMASCOPE-RES-16K
    6. 819
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations related to derivatives and algebraic operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessType
    -0.52
    omock
    -0.41
     AppBar
    -0.40
    cstdio
    -0.40
    IsContent
    -0.40
    لفة
    -0.40
     Scrooge
    -0.40
     TableColumn
    -0.39
     onBackPressed
    -0.39
    kost
    -0.38
    POSITIVE LOGITS
    Y
    1.37
    getY
    1.36
     y
    1.36
     Y
    1.34
    setY
    1.27
    y
    1.24
     getY
    1.11
    SY
    1.10
    Yy
    1.09
     yard
    1.06
    Activations Density 0.643%

    No Known Activations