© 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. 13318
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a small quantity or number of items

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

    "few"

    np_acts-logits-general · gemini-2.0-flash

    few + count

    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
    GenerationType
    -0.54
    araman
    -0.47
     Hartmann
    -0.44
     Hartman
    -0.44
    abestanden
    -0.40
    BrowserModule
    -0.39
     BrowserModule
    -0.39
     épaules
    -0.39
    TGA
    -0.39
     Matheson
    -0.39
    POSITIVE LOGITS
     few
    1.16
    Few
    1.15
     FEW
    1.05
     Few
    1.03
    few
    1.02
     dozen
    0.90
     wenige
    0.85
     wenigen
    0.79
     poucos
    0.77
    Quelques
    0.76
    Activations Density 0.041%

    No Known Activations