© 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. 25-GEMMASCOPE-RES-16K
    11. 9238
    Prev
    Next
    INDEX
    Explanations

    patterns or structures related to charts and graphs

    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
     (&
    -0.59
    BeginContext
    -0.55
    ?”,
    -0.51
    amp
    -0.50
    &
    -0.50
    ,&
    -0.48
    FXML
    -0.48
    ‎
    -0.47
    : 
    -0.46
    AddTagHelper
    -0.46
    POSITIVE LOGITS
    PARATOR
    0.61
    ooooo
    0.61
    oooooooo
    0.59
    ATURA
    0.57
    oooooo
    0.57
    oooooooooooooooo
    0.56
    oooo
    0.56
    بوابة
    0.56
    Приятного
    0.56
    ooooooo
    0.56
    Activations Density 0.653%

    No Known Activations