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. 2949
    Prev
    Next
    INDEX
    Explanations

    structured data and programming language elements

    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
     AliExpress
    -0.59
    CppMethod
    -0.59
    QMetaType
    -0.58
     Nop
    -0.53
     Richt
    -0.51
     parten
    -0.51
    OGND
    -0.49
     Arka
    -0.48
    meaux
    -0.48
    íncia
    -0.46
    POSITIVE LOGITS
     مرئيه
    0.79
    selectAll
    0.70
    новниш
    0.59
     Baltimore
    0.58
    Minnesota
    0.57
    Baltimore
    0.56
     ddelweddau
    0.56
    nesota
    0.55
     Minnesota
    0.52
    ազմ
    0.51
    Activations Density 0.078%

    No Known Activations