© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 76757
    Prev
    Next
    INDEX
    Explanations

    references to confrontations or competitive encounters

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

    duel, shootout, sparring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     informée
    -0.51
     Autorisations
    -0.49
    Mariana
    -0.48
    Distribuzione
    -0.47
     Macmillan
    -0.46
    byshire
    -0.45
     surla
    -0.45
    gráfica
    -0.45
     Packer
    -0.45
    MLLoader
    -0.44
    POSITIVE LOGITS
     duel
    1.93
     Duel
    1.85
    Duel
    1.67
    duel
    1.58
     duels
    1.55
     duelo
    1.24
     duet
    0.86
     battle
    0.82
     showdown
    0.78
    battle
    0.73
    Activations Density 0.004%

    No Known Activations