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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 14835
    Prev
    Next
    INDEX
    Explanations

    logical structures and query syntax in technical writing

    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
     ujednoznacz
    -0.69
    RenderAtEndOf
    -0.65
    évaluateur
    -0.63
    ValueStyle
    -0.63
     trattano
    -0.63
    tagHelperRunner
    -0.61
     makeStyles
    -0.54
    NavController
    -0.54
    URLException
    -0.53
    CppMethod
    -0.53
    POSITIVE LOGITS
    AntiForgeryToken
    0.72
    InteropServices
    0.62
    WriteTagHelper
    0.51
    reet
    0.49
    ContentAsync
    0.49
     ImportError
    0.48
    责任编辑
    0.46
    ÚBL
    0.45
     cấp
    0.45
     %).
    0.45
    Activations Density 1.499%

    No Known Activations