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. 15158
    Prev
    Next
    INDEX
    Explanations

    words related to references, attention, or consideration towards specific subjects

    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
    ceton
    -0.79
     impatience
    -0.77
     Chet
    -0.74
    طلاق
    -0.67
    Искәрмәләр
    -0.67
     {$\
    -0.66
     Popper
    -0.66
    omalainen
    -0.66
    kit
    -0.66
     batteries
    -0.65
    POSITIVE LOGITS
    IBarButtonItem
    0.98
     regarding
    0.87
     Regarding
    0.84
     متعلقه
    0.84
    regarding
    0.83
     REGARD
    0.81
    nitus
    0.79
     AssemblyTitle
    0.79
     herein
    0.78
     thereof
    0.76
    Activations Density 0.171%

    No Known Activations