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. 25-GEMMASCOPE-RES-16K
    6. 3548
    Prev
    Next
    INDEX
    Explanations

    technical terms related to automotive parts and enhancements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.74
     referrerpolicy
    -0.57
     approfon
    -0.48
     descubrimiento
    -0.48
     colchón
    -0.47
    Filmografie
    -0.46
     للتو
    -0.46
    ghijklmnop
    -0.46
    viating
    -0.45
     scoper
    -0.45
    POSITIVE LOGITS
     aesthetically
    1.65
     aesthetic
    1.50
     aesthetics
    1.47
     visually
    1.45
    aesthetic
    1.31
     Aesthetic
    1.29
    Aesthetic
    1.29
     looks
    1.27
     estético
    1.26
     estética
    1.26
    Activations Density 0.391%

    No Known Activations