© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 2033
    Prev
    Next
    INDEX
    Explanations

    references to different levels of energy or low/high specifications in materials or measurements

    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
     cuadrada
    -0.58
    CodedInputStream
    -0.57
     seguinte
    -0.54
     señ
    -0.50
     blevet
    -0.49
     recib
    -0.49
     obrigado
    -0.49
     समीक्षाएं
    -0.49
     fiecare
    -0.48
     scopri
    -0.48
    POSITIVE LOGITS
     NSCoder
    0.75
    ("")]
    
    0.71
    extAlignment
    0.63
    ]-'
    0.63
    رشف
    0.62
    thâu
    0.61
    isticated
    0.61
    ########.
    0.59
     moderate
    0.58
    RoutingModule
    0.58
    Activations Density 0.645%

    No Known Activations