© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6537
    Prev
    Next
    INDEX
    Explanations

    instances of legal and procedural terminology related to jury management

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

    Tokens after colons, double asterisks, or periods

    np_acts-logits-general · gemini-2.0-flash

    section headers and funding information

    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
    Spoljašnje
    -0.81
    webElementXpaths
    -0.79
     Myself
    -0.79
     Chwiliwch
    -0.75
    RTEE
    -0.73
    !*\
    -0.73
    Yourself
    -0.72
    şiv
    -0.72
     kaarangay
    -0.71
     Itself
    -0.71
    POSITIVE LOGITS
    onAttach
    0.46
     unha
    0.41
    ">'.$
    0.40
     unde
    0.39
     reclamation
    0.39
     thorium
    0.38
     Οι
    0.38
    超时
    0.37
     eccl
    0.37
     کور
    0.36
    Activations Density 0.158%

    No Known Activations