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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 17-GEMMASCOPE-RES-16K
    6. 7341
    Prev
    Next
    INDEX
    Explanations

    code segments that involve sorting algorithms, particularly focusing on median or average calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.60
     StatefulWidget
    -0.53
    SuccessListener
    -0.49
    nestjs
    -0.49
    .*")]
    -0.44
    ppig
    -0.44
     مشين
    -0.43
     eri
    -0.43
    nloa
    -0.43
    devamını
    -0.42
    POSITIVE LOGITS
    Replacing
    0.84
     replace
    0.80
     replacing
    0.79
     swap
    0.77
    swap
    0.76
     cser
    0.75
     replaces
    0.75
     swapping
    0.74
     Replacing
    0.73
     sostitu
    0.72
    Activations Density 0.076%

    No Known Activations