© 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. 20-GEMMASCOPE-RES-16K
    11. 5855
    Prev
    Next
    INDEX
    Explanations

    references and terms related to the current state or status of an object or variable in programming contexts

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

    Preceding or following "current" or "previous"

    np_acts-logits-general · gemini-2.0-flash

    sequence or position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.65
    ″]
    -0.64
    }{*}{}
    -0.62
    PyExc
    -0.61
    ')):
    -0.60
    "){
    -0.60
    KommentareTeilen
    -0.59
    //
    -0.59
    Économie
    -0.58
    ($__
    -0.58
    POSITIVE LOGITS
     vertes
    0.61
     nonzero
    0.56
     ones
    0.52
     Monfieur
    0.51
    EndContext
    0.51
     pior
    0.50
    NonNull
    0.50
    तम
    0.48
    껄
    0.47
    꺼
    0.47
    Activations Density 0.369%

    No Known Activations