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. 20-GEMMASCOPE-RES-16K
    6. 14021
    Prev
    Next
    INDEX
    Explanations

    technical terms and processes related to app deployment and service management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     soms
    -0.73
    UserScript
    -0.70
    AutoScaleMode
    -0.69
    Portail
    -0.64
     zelfs
    -0.61
     Gegenteil
    -0.60
     mxArray
    -0.58
     bazen
    -0.57
    십시오
    -0.55
    LayoutStyle
    -0.55
    POSITIVE LOGITS
     we
    0.76
    Notice
    0.72
     Notice
    0.72
     now
    0.70
     here
    0.67
    さっき
    0.65
     notice
    0.64
    我们将
    0.62
    Now
    0.61
     pretty
    0.60
    Activations Density 0.541%

    No Known Activations