© 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. 30-GEMMASCOPE-RES-16K
    6. 10743
    Prev
    Next
    INDEX
    Explanations

    phrases related to success and victories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    associated with winning or defeating

    np_acts-logits-general · gemini-2.0-flash

    election or competition outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ंदीखरीदारी
    -0.51
    AndEndTag
    -0.39
    UserScript
    -0.39
    TagMode
    -0.37
     himo
    -0.35
    жнему
    -0.34
    colage
    -0.34
     aceptas
    -0.33
    szt
    -0.32
    MessageTagHelper
    -0.31
    POSITIVE LOGITS
     victory
    2.23
     win
    2.09
     wins
    1.98
     victories
    1.84
     winning
    1.84
    victory
    1.73
     vitória
    1.69
     kemenangan
    1.62
     victoire
    1.61
     Victory
    1.59
    Activations Density 0.324%

    No Known Activations