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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 1686
    Prev
    Next
    INDEX
    Explanations

    the definite article "Der" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.66
     Please
    -0.62
     natural
    -0.56
     ang
    -0.55
     naturally
    -0.54
    Please
    -0.54
     It
    -0.52
    psis
    -0.52
    рина
    -0.52
    ↵↵
    -0.51
    POSITIVE LOGITS
    脚注の使い方
    1.10
    RenderAtEndOf
    1.05
     utafitiHapana
    0.99
     AssemblyCulture
    0.92
     мәкал
    0.89
    Datuak
    0.89
    SharedDtor
    0.88
    unhofer
    0.87
     pinulongan
    0.86
    دانشنامهٔ
    0.85
    Activations Density 0.399%

    No Known Activations