© 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. 9-GEMMASCOPE-RES-16K
    11. 2055
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific formatting or structure in the text, such as parenthesis and separation of elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.58
    LookAnd
    -0.51
     comigo
    -0.50
    ItemBackground
    -0.48
     sonno
    -0.48
     chromos
    -0.48
     jsPsych
    -0.47
     ricord
    -0.47
    Արտաքին
    -0.47
    uli
    -0.47
    POSITIVE LOGITS
      (
    0.77
    |}{$
    0.75
    ± 
    0.67
    İstinadlar
    0.65
    それとも
    0.65
    $}}
    0.65
    最快更新
    0.64
    igail
    0.61
    intenance
    0.61
    BeginContext
    0.61
    Activations Density 0.759%

    No Known Activations