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. 12908
    Prev
    Next
    INDEX
    Explanations

    programming and data serialization concepts, particularly related to XML and JSON handling within a codebase

    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
    WebElementEntity
    -0.92
    contentLoaded
    -0.77
    LookAnd
    -0.75
     pinulongan
    -0.67
    ///</
    -0.66
    __(/*!
    -0.66
     betweenstory
    -0.66
    Parcelize
    -0.64
    人民共和国
    -0.63
    UnusedPrivate
    -0.62
    POSITIVE LOGITS
    urlopen
    0.66
    PrintWriter
    0.62
     pageContext
    0.59
    ImageContext
    0.59
    ResponseWriter
    0.56
    WritableDatabase
    0.53
    DataInputStream
    0.52
    openConnection
    0.52
    getWriter
    0.51
    Jedis
    0.51
    Activations Density 0.329%

    No Known Activations