Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10267
    Prev
    Next
    INDEX
    Explanations

    components and features related to technology and electronics, particularly in the context of consumer products

    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
     odious
    -0.60
     immoral
    -0.59
     repugnant
    -0.59
     disgrace
    -0.58
     indignant
    -0.58
     abhor
    -0.58
     barbarous
    -0.57
     sorrowful
    -0.57
     abominable
    -0.57
     wretched
    -0.56
    POSITIVE LOGITS
     DJI
    0.62
     GoPro
    0.58
     VPN
    0.57
     smartwatch
    0.57
     laptops
    0.57
     IPTV
    0.56
     laptop
    0.56
     IoT
    0.55
     Bluetooth
    0.54
     CNC
    0.54
    Activations Density 17.615%

    No Known Activations