© 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. 1695
    Prev
    Next
    INDEX
    Explanations

    phrases involving relationships or associations indicated by the word "with"

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

    "with" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    with Independent

    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
    GOTREF
    -0.50
     perſon
    -0.45
     ſtand
    -0.44
     ſou
    -0.42
     ſtate
    -0.41
     houſe
    -0.40
     ſon
    -0.37
     fubject
    -0.37
     Gerechtigkeit
    -0.35
     Gegenstand
    -0.35
    POSITIVE LOGITS
     nahilalakip
    0.71
     surla
    0.67
    ⟬
    0.66
     فريبيس
    0.66
     Normdatei
    0.65
    holds
    0.64
    带有
    0.63
    новниш
    0.62
     עם
    0.60
     diserta
    0.60
    Activations Density 0.450%

    No Known Activations