© 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. 1666
    Prev
    Next
    INDEX
    Explanations

    phrases indicating common occurrences or frequencies of topics and concepts

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

    "common" or "commonly"

    np_acts-logits-general · gemini-2.0-flash

    common or frequently occurring

    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
    StoryboardSegue
    -0.84
    Personendaten
    -0.73
    makeConstraints
    -0.64
    AddTagHelper
    -0.60
     disambiguazione
    -0.59
     Exacts
    -0.57
    ViewInit
    -0.56
    IntoConstraints
    -0.54
     Geſch
    -0.54
    ngrx
    -0.53
    POSITIVE LOGITS
     common
    0.81
     frequently
    0.75
     commonly
    0.74
     frequent
    0.70
     Common
    0.66
    Common
    0.65
    common
    0.64
    常见
    0.64
    常見
    0.63
     popular
    0.63
    Activations Density 0.413%

    No Known Activations