© 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 - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 8832
    Prev
    Next
    INDEX
    Explanations

    the letter "e" with varying frequencies, indicating a focus on its prevalence in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rhosis
    -1.05
    )");
    -1.00
     архивлан
    -0.93
     >=",
    -0.89
     */
    -0.88
     bezeichneter
    -0.86
    )";
    -0.85
    Tikang
    -0.84
     triom
    -0.81
    }\]
    -0.80
    POSITIVE LOGITS
    e
    1.36
     e
    1.33
    E
    1.33
     E
    1.13
    getE
    0.85
    𝚎
    0.83
     ge
    0.81
     jöv
    0.81
    Ge
    0.80
    ge
    0.80
    Activations Density 0.149%

    No Known Activations