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. 10-GEMMASCOPE-RES-16K
    6. 13134
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics related to health or research studies

    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
     متعلقه
    -1.02
    ГЛА
    -1.02
     Paglinawan
    -0.94
    ########.
    -0.88
     Grease
    -0.86
     Khe
    -0.86
    ]]
    
    -0.86
     scher
    -0.86
    )))
    
    -0.82
     propter
    -0.81
    POSITIVE LOGITS
    0
    0.83
    شرين
    0.71
     २०
    0.70
     faveur
    0.67
    wanzig
    0.65
    ıç
    0.64
     veinte
    0.64
     oxalate
    0.63
     trå
    0.62
     volna
    0.61
    Activations Density 0.269%

    No Known Activations