© 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. 12453
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and references to entities, specifically "it" and "they"

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

    "it" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    it followed by a verb

    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
    ']==
    -0.35
     ...
    -0.35
     +
    -0.30
    ]==
    -0.30
     Var
    -0.29
    RegressionTest
    -0.29
     Buss
    -0.29
    yn
    -0.28
     x
    -0.28
     ×
    -0.28
    POSITIVE LOGITS
    ſelf
    0.76
    ſelves
    0.74
    ähteet
    0.71
    majánló
    0.70
     témoig
    0.70
    堔
    0.70
     Majefty
    0.68
    awarkan
    0.66
     メンテナ
    0.66
     Italij
    0.66
    Activations Density 0.344%

    No Known Activations