© 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. 24-GEMMASCOPE-RES-16K
    6. 4867
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements, particularly brackets and parentheses

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

    Closing parenthesis

    np_acts-logits-general · gemini-2.0-flash

    closing punctuation followed by code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WaitGroup
    -0.69
    #
    -0.59
    contentLoaded
    -0.59
    TypedDataSet
    -0.57
    SearchParams
    -0.56
    BASEPATH
    -0.56
     memer
    -0.56
    خواندن
    -0.56
     Bom
    -0.53
    enterOuterAlt
    -0.50
    POSITIVE LOGITS
     )
    0.57
    OGND
    0.56
     )
    
    0.51
     );
    0.49
     );
    
    0.49
    zwischen
    0.48
     ){
    0.47
    RTDA
    0.46
    ستی
    0.45
    いる
    0.45
    Activations Density 0.141%

    No Known Activations