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. 15-GEMMASCOPE-RES-16K
    6. 2868
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax elements, including variable declarations and method definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     or
    -0.55
     non
    -0.54
     Federal
    -0.53
     miss
    -0.50
     Fort
    -0.50
     
    -0.49
    baseURL
    -0.47
     federal
    -0.47
    لاس
    -0.47
     "
    -0.47
    POSITIVE LOGITS
     HasFactory
    1.06
     المعيارى
    1.00
    \{\\
    0.99
    SharedCtor
    0.94
     فريبيس
    0.93
    EndContext
    0.91
     surla
    0.90
     Paglinawan
    0.87
    Portail
    0.86
     Signalez
    0.86
    Activations Density 0.025%

    No Known Activations