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. 20-GEMMASCOPE-RES-16K
    6. 5151
    Prev
    Next
    INDEX
    Explanations

    concepts related to institutions and their governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding or containing non-English characters

    np_acts-logits-general · gemini-2.0-flash

    related to programming syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     curated
    -0.61
    ⁣
    -0.56
    ​
    -0.54
     incroy
    -0.54
     onboarding
    -0.53
     revanche
    -0.53
     prepping
    -0.52
     membuatnya
    -0.52
    vsk
    -0.51
     humains
    -0.51
    POSITIVE LOGITS
     biß
    0.86
    DoubleQuotes
    0.79
     daß
    0.73
    ()]
    
    0.73
    SourceChecksum
    0.72
    });*/
    0.71
     Daß
    0.69
    ondissement
    0.69
    Sucesor
    0.69
    Contd
    0.68
    Activations Density 0.198%

    No Known Activations