© 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. 7828
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the need for effort or time to achieve something

    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
     betweenstory
    -0.59
    httphttps
    -0.49
    principalColumn
    -0.49
    Спасылкі
    -0.47
     Wicidata
    -0.46
     mxArray
    -0.46
    entuh
    -0.44
     Gerade
    -0.44
     تضيفلها
    -0.43
    SPJ
    -0.42
    POSITIVE LOGITS
     takes
    0.96
     Takes
    0.91
    Takes
    0.87
    takes
    0.85
     занимает
    0.63
     dauert
    0.59
     waited
    0.54
     demora
    0.54
     requires
    0.50
     braucht
    0.50
    Activations Density 0.161%

    No Known Activations