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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 2000
    Prev
    Next
    INDEX
    Explanations

    mentions of addresses in various contexts

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

    "address" and related terms

    np_acts-logits-general · gemini-2.0-flash

    address or requirement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    coaster
    -0.68
    EndInit
    -0.65
    Anhalt
    -0.62
    phrine
    -0.62
    Према
    -0.62
    RLock
    -0.60
    AccessException
    -0.60
    herald
    -0.58
    ContentAsync
    -0.58
     Weldon
    -0.58
    POSITIVE LOGITS
     getAddress
    0.94
     Addresses
    0.94
    addresses
    0.87
    Addresses
    0.85
     addresses
    0.80
     ADDRESS
    0.76
     地址
    0.76
    ograph
    0.76
    able
    0.74
     addr
    0.67
    Activations Density 0.041%

    No Known Activations