© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 297
    Prev
    Next
    INDEX
    Explanations

    indications of computational or programming content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical references to observational equipment and data collection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Solar observation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.55
    ReusableCell
    -0.53
    haupt
    -0.43
    //
    -0.43
    mässig
    -0.43
     gange
    -0.42
    heiser
    -0.41
    stands
    -0.41
    +#+#
    -0.41
     below
    -0.40
    POSITIVE LOGITS
     telescope
    0.69
     amateurs
    0.63
    IUrlHelper
    0.62
     Telescope
    0.61
    MethodManager
    0.61
    帖最后由
    0.61
    تفصیلات
    0.60
    tagHelperRunner
    0.59
     Planets
    0.59
     cursory
    0.59
    Activations Density 0.009%

    No Known Activations