© 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-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 3872
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "das" (meaning "the" in German)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.54
    новниш
    -0.52
    ########.
    -0.52
     onOptions
    -0.50
    saraba
    -0.49
    MetaObject
    -0.49
     tolua
    -0.48
     ComVisible
    -0.47
    اریخ
    -0.47
    MethodManager
    -0.47
    POSITIVE LOGITS
    das
    1.12
     dash
    1.12
     Das
    1.12
     das
    1.08
    Das
    1.08
    dash
    1.04
     Dash
    0.98
     dashes
    0.98
     DAS
    0.95
    Dash
    0.92
    Activations Density 0.085%

    No Known Activations