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

    Neuronpedia

    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. 8524
    Prev
    Next
    INDEX
    Explanations

    data structures and method calls in code related to request handling

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

    Tokens followed by "req" or "REQ"

    np_acts-logits-general · gemini-2.0-flash

    request/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
    CppCodeGen
    -0.62
     ROM
    -0.57
     dial
    -0.53
     lari
    -0.53
     Lovel
    -0.52
     Kul
    -0.51
     Brid
    -0.51
     Dalton
    -0.51
    >--}}
    -0.51
    lashed
    -0.50
    POSITIVE LOGITS
    req
    2.60
     req
    2.56
    Req
    2.22
     Req
    2.15
    REQ
    1.98
     REQ
    1.80
     requirement
    1.70
     Requirement
    1.69
     Requ
    1.68
    reqs
    1.63
    Activations Density 0.108%

    No Known Activations