© 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. 21-GEMMASCOPE-RES-16K
    11. 1557
    Prev
    Next
    INDEX
    Explanations

    the name "Ko" and variations of it as well as the occurrences of the word "Zoho."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    に
    -0.79
    是
    -0.78
    ۰
    -0.69
    Hozzáférés
    -0.67
     تضيفلها
    -0.66
    DeleteBehavior
    -0.63
    น้อง
    -0.60
    ples
    -0.59
    MigrationBuilder
    -0.57
    p
    -0.57
    POSITIVE LOGITS
    й
    0.57
    locating
    0.51
    er
    0.51
    load
    0.49
     traditionnels
    0.48
    pejo
    0.48
    incident
    0.46
     abrigo
    0.46
    care
    0.46
    pole
    0.45
    Activations Density 0.206%

    No Known Activations