© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 11643
    Prev
    Next
    INDEX
    Explanations

    specific job recruitment details or opportunities

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

    Symbols and punctuation

    np_acts-logits-general · gemini-2.0-flash

    how to make

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.76
     "..\..\
    -0.67
     "..\..\..\
    -0.62
    CopyWith
    -0.59
    expandindo
    -0.58
     onBind
    -0.57
     AssemblyProduct
    -0.57
     iprot
    -0.57
    RenderAtEndOf
    -0.56
     plomo
    -0.55
    POSITIVE LOGITS
    =$?
    0.63
    })$}
    0.60
    uesday
    0.59
     ReSharper
    0.56
    Sociedad
    0.55
     < 
    0.55
    )’
    0.54
    íncia
    0.54
    //};
    0.53
    NUMX
    0.53
    Activations Density 0.015%

    No Known Activations