© 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. 2-GEMMASCOPE-RES-16K
    6. 12849
    Prev
    Next
    INDEX
    Explanations

    references to people, specifically personal pronouns

    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
     дописавши
    -0.50
     BoxFit
    -0.49
     يتيمه
    -0.46
    queryInterface
    -0.45
    JspWriter
    -0.45
     وتسجيلات
    -0.44
     defaultstate
    -0.44
    AndroidJUnit
    -0.44
     NavController
    -0.43
    Inst
    -0.43
    POSITIVE LOGITS
     mentre
    0.50
     mientras
    0.47
     bambú
    0.44
     Mentre
    0.43
    ในการ
    0.43
     enquanto
    0.43
     podczas
    0.43
     while
    0.42
    TagMode
    0.41
     Découvrez
    0.41
    Activations Density 0.296%

    No Known Activations