© 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. 24-GEMMASCOPE-RES-16K
    6. 3849
    Prev
    Next
    INDEX
    Explanations

    financial metrics and figures

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

    Numbers followed by "M" or similar abbreviations

    np_acts-logits-general · gemini-2.0-flash

    District Court

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oredCriteria
    -0.63
    SharedDtor
    -0.63
    BeginInit
    -0.53
     DBNull
    -0.53
     linkovi
    -0.50
    AnchorStyles
    -0.50
    Vegeu
    -0.50
    invokeLater
    -0.49
    iecie
    -0.49
    asanjo
    -0.49
    POSITIVE LOGITS
    k
    1.02
    K
    0.87
    M
    0.86
    mo
    0.64
    eqn
    0.60
    m
    0.59
    kish
    0.59
    min
    0.58
    pax
    0.58
    mn
    0.57
    Activations Density 0.634%

    No Known Activations