© 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-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 3530
    Prev
    Next
    INDEX
    Explanations

    mentions of addresses within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iwa
    -0.69
    Redacción
    -0.69
    mények
    -0.67
    Kjelder
    -0.67
     Fland
    -0.67
    kuper
    -0.67
    Referințe
    -0.67
     Wyman
    -0.67
    ²/
    -0.66
     Pitman
    -0.65
    POSITIVE LOGITS
     ADDRESS
    1.71
     Addresses
    1.67
     address
    1.66
     addresses
    1.64
     Address
    1.61
    address
    1.60
    Addresses
    1.57
    Address
    1.52
    addresses
    1.50
    ADDRESS
    1.49
    Activations Density 0.044%

    No Known Activations