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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4-GEMMASCOPE-RES-16K
    6. 15940
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate inquiry and exploration of ideas or theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    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
    -0.48
     aras
    -0.46
    InitVars
    -0.45
    日月
    -0.45
    existsSync
    -0.43
    /***/
    -0.43
    ↵↵
    -0.42
    ObjectModel
    -0.42
    ://"
    -0.42
     aient
    -0.42
    POSITIVE LOGITS
    Portale
    0.64
    GIVEREF
    0.62
    ToScroll
    0.61
    byshev
    0.60
    haviour
    0.59
    CppCodeGen
    0.59
     فريبيس
    0.57
    Zeneca
    0.56
    ingale
    0.56
    SupportActionBar
    0.56
    Activations Density 0.481%

    No Known Activations