© 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. 16175
    Prev
    Next
    INDEX
    Explanations

    numeric identifiers or codes, particularly in a structured format or specification

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

    The number 3 or related to it

    np_acts-logits-general · gemini-2.0-flash

    3 followed by GPP or G

    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
    ../../../
    -0.86
    UnknownFields
    -0.86
    ']))
    -0.84
    دانشنامهٔ
    -0.77
     للمعارف
    -0.74
    ので
    -0.73
    ərbaycan
    -0.73
    omiast
    -0.72
     Pues
    -0.72
     Walkover
    -0.71
    POSITIVE LOGITS
    rd
    1.67
    3
    1.15
    GPP
    0.84
     rd
    0.81
    prnewswire
    0.78
    rds
    0.76
    ßig
    0.74
    6
    0.73
    5
    0.72
    0
    0.71
    Activations Density 1.379%

    No Known Activations