© 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. 28-GEMMASCOPE-RES-16K
    6. 4044
    Prev
    Next
    INDEX
    Explanations

    words related to winning or victories in various contexts

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

    winning or having won

    np_acts-logits-general · gemini-2.0-flash

    winning competitions or elections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SuppressLint
    -0.37
     docentes
    -0.35
    BaseController
    -0.34
    ViewFeatures
    -0.34
     VIAF
    -0.34
    SearchParams
    -0.33
     către
    -0.32
    amoja
    -0.32
     Grundlage
    -0.31
     Haushalt
    -0.31
    POSITIVE LOGITS
     battles
    0.78
     battle
    0.73
     BATTLE
    0.69
     won
    0.68
     win
    0.65
     Battle
    0.65
    battle
    0.64
     Battles
    0.63
     hearts
    0.61
     competitions
    0.60
    Activations Density 0.141%

    No Known Activations