© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12570
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation and formatting related to pauses or breaks in text

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

    End of turn token

    np_acts-logits-general · gemini-2.0-flash

    Title, hospital, clinic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     ujednoznacz
    -0.78
     autorytatywna
    -0.77
    ValueStyle
    -0.75
    UrlResolution
    -0.74
     disambiguazione
    -0.73
    CppMethod
    -0.72
    الحياه
    -0.70
    AddTagHelper
    -0.67
    rungsseite
    -0.66
     оригіналу
    -0.66
    POSITIVE LOGITS
    <eos>
    0.36
     Pal
    0.35
    usammen
    0.33
     Title
    0.33
     Born
    0.32
     So
    0.30
     die
    0.30
     tal
    0.29
     Die
    0.29
     Fos
    0.29
    Activations Density 0.667%

    No Known Activations