© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9917
    Prev
    Next
    INDEX
    Explanations

    dialogue related to authority and responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cæsar
    -0.64
     blazer
    -0.63
     Mussolini
    -0.63
     EconPapers
    -0.61
    MLLoader
    -0.60
     Khrushchev
    -0.60
     chauffeur
    -0.60
     garage
    -0.58
     fotograf
    -0.58
    الدراسه
    -0.58
    POSITIVE LOGITS
     swords
    0.47
     sword
    0.42
     archery
    0.42
    ValueStyle
    0.40
     kılı
    0.40
    Ӕ
    0.39
     horses
    0.39
     Schwert
    0.39
     paard
    0.39
    🗡
    0.39
    Activations Density 0.593%

    No Known Activations