© 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. 10139
    Prev
    Next
    INDEX
    Explanations

    evaluative statements based on evidence and conclusions drawn from arguments or trials

    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
     ویکی‌پدیای
    -0.92
     beginnetje
    -0.81
    AutoField
    -0.78
     otomatig
    -0.74
    alamu
    -0.71
    bewerken
    -0.71
    duff
    -0.71
    éndolo
    -0.69
    ']").
    -0.68
    最快更新
    -0.68
    POSITIVE LOGITS
     that
    1.22
     bahwa
    0.98
     bahawa
    0.81
     rằng
    0.79
    ว่า
    0.78
     kwamba
    0.72
     realizes
    0.72
     said
    0.69
     ότι
    0.68
     stated
    0.65
    Activations Density 0.967%

    No Known Activations