© 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 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. 8624
    Prev
    Next
    INDEX
    Explanations

    specific characters or symbols in the text, particularly those related to punctuation or special formatting

    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
    دانشنامهٔ
    -0.73
     '\\;'
    -0.69
    keyColumn
    -0.62
     betweenstory
    -0.62
     Shee
    -0.62
     médicas
    -0.61
     صوتيه
    -0.60
    PageContext
    -0.60
     suivants
    -0.59
    хьтан
    -0.58
    POSITIVE LOGITS
    \'
    0.83
    '
    0.70
    cshtml
    0.69
    FontStyle
    0.64
     externes
    0.63
    ´
    0.62
    rsquo
    0.61
    LikeLike
    0.61
    tagHelperRunner
    0.60
     endwhile
    0.60
    Activations Density 0.066%

    No Known Activations