Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 10992
    Prev
    Next
    INDEX
    Explanations

    instances of introductory transitions or context-setting phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    非常的
    -0.82
    maktadır
    -0.70
     skall
    -0.69
     Whilst
    -0.69
     אשר
    -0.64
    mıştır
    -0.64
     diatas
    -0.63
     данного
    -0.63
    Whilst
    -0.63
    很多的
    -0.62
    POSITIVE LOGITS
     staffers
    0.85
     pricey
    0.81
     enggak
    0.81
    £
    0.79
     yore
    0.72
     itſelf
    0.72
     swears
    0.71
     houſe
    0.71
     reafon
    0.70
     lenker
    0.70
    Activations Density 0.386%

    No Known Activations