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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 2597
    Prev
    Next
    INDEX
    Explanations

    references to code snippets or technical terms related to programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddHtmlAttribute
    -0.64
     boarding
    -0.57
    WEBPACK
    -0.54
     Boarding
    -0.52
    Boarding
    -0.52
    posedge
    -0.50
    +#+#
    -0.47
     للاسماء
    -0.45
    ieh
    -0.45
     inoxidable
    -0.45
    POSITIVE LOGITS
     map
    3.78
     Map
    3.46
    map
    3.38
    Map
    3.20
     maps
    2.76
     MAP
    2.67
    MAP
    2.61
     Maps
    2.52
     mapa
    2.43
    getMap
    2.31
    Activations Density 0.359%

    No Known Activations