© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 11813
    Prev
    Next
    INDEX
    Explanations

    structured data representations, particularly those involving brackets and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ing
    -0.61
    豁
    -0.61
    indrome
    -0.60
    Nox
    -0.60
    Ars
    -0.60
     CreateTagHelper
    -0.60
    amoan
    -0.59
     delar
    -0.59
    ariot
    -0.58
    brada
    -0.58
    POSITIVE LOGITS
    IActionResult
    0.70
    Collegamenti
    0.63
    tagext
    0.62
     todav
    0.61
    {\
    0.58
    npmjs
    0.57
    IonicModule
    0.57
    ISupport
    0.56
     actionTypes
    0.56
    Trish
    0.56
    Activations Density 1.198%

    No Known Activations