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. 66
    Prev
    Next
    INDEX
    Explanations

    keywords and structural elements related to Python modules and functions

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

    Code snippets using Python or similar

    np_acts-logits-general · gemini-2.0-flash

    module and class initialization

    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
    ")){
    
    -0.48
     mukana
    -0.47
    idän
    -0.47
    */}
    -0.47
    ']))
    
    -0.45
    )•
    -0.45
     tider
    -0.43
    }}"
    -0.43
     sveta
    -0.43
    )"),
    -0.42
    POSITIVE LOGITS
     nahilalakip
    0.87
    SequentialGroup
    0.78
     ISNI
    0.76
    cshtml
    0.76
    styleable
    0.74
    LookAnd
    0.73
     Italijanski
    0.73
    #+#
    0.70
    
    0.69
     BorderRadius
    0.68
    Activations Density 0.985%

    No Known Activations