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. 8-GEMMASCOPE-RES-16K
    6. 8175
    Prev
    Next
    INDEX
    Explanations

    specific start or end markers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contextLoads
    -0.82
     Romains
    -0.82
     attiv
    -0.77
    seamnă
    -0.75
    ρισ
    -0.71
    addContainerGap
    -0.71
     rodríguez
    -0.70
     vixion
    -0.70
     Leland
    -0.69
    corrência
    -0.69
    POSITIVE LOGITS
     Que
    1.10
    Que
    1.10
     que
    1.07
     QUE
    0.98
    que
    0.92
    __":
    
    0.91
     że
    0.89
    RenderAtEndOf
    0.89
    Qui
    0.85
    ║
    0.84
    Activations Density 0.052%

    No Known Activations