© 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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15474
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of quantity or frequency in relation to specific items or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.73
     uſe
    -0.68
     myſelf
    -0.62
     RSSSF
    -0.61
     stuff
    -0.61
    věř
    -0.58
     csal
    -0.58
    ︎
    -0.58
     Lycée
    -0.57
     NFA
    -0.57
    POSITIVE LOGITS
    /**
    0.94
     InputDecoration
    0.89
     two
    0.81
    TWO
    0.79
    ">//
    0.78
    ății
    0.78
     yksi
    0.76
     nahilalakip
    0.75
    msgSender
    0.74
    another
    0.73
    Activations Density 0.056%

    No Known Activations