© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 1096
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their properties in scientific contexts

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

    Inequality relationships (greater than, less than)

    np_acts-logits-general · gemini-2.0-flash

    comparisons and rankings

    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
     (_,
    -0.45
    :')
    -0.44
    :}
    -0.43
    ]++;
    -0.43
    :");
    
    -0.42
    キシ
    -0.42
    ]+=
    -0.41
    ________________
    -0.39
    \#:
    -0.37
    POSITIVE LOGITS
     betweenstory
    0.89
    AccessorTable
    0.79
    PreferredItem
    0.75
    ItemBackground
    0.74
     resourceCulture
    0.71
    webElementXpaths
    0.70
    ftagPool
    0.69
    dafx
    0.67
    +#+#
    0.66
     ostavi
    0.66
    Activations Density 1.031%

    No Known Activations