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. 2664
    Prev
    Next
    INDEX
    Explanations

    references to samples in experimental or scientific contexts

    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
     defaultstate
    -0.77
     fuoco
    -0.71
     Beh
    -0.69
    ziem
    -0.67
    VIAF
    -0.65
    sertation
    -0.64
     Ush
    -0.63
     CURLOPT
    -0.62
    ++
    
    -0.62
    Referințe
    -0.62
    POSITIVE LOGITS
     Samples
    1.75
     samples
    1.75
     Sample
    1.64
     SAMPLE
    1.63
    samples
    1.59
    Samples
    1.57
    Sample
    1.56
     sample
    1.54
     Samp
    1.51
    sample
    1.45
    Activations Density 0.092%

    No Known Activations