© 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. 14036
    Prev
    Next
    INDEX
    Explanations

    issues related to contractual obligations and agreements

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

    agreements or promises

    np_acts-logits-general · gemini-2.0-flash

    promises and agreements

    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
     Administrativna
    -0.45
    pil
    -0.40
     Sach
    -0.40
     Huk
    -0.40
     akt
    -0.39
    BeginInit
    -0.38
     Pilots
    -0.38
    ulka
    -0.38
     Pairing
    -0.38
    Blick
    -0.37
    POSITIVE LOGITS
     promised
    0.54
     propOrder
    0.54
    FunctionFlags
    0.54
     promessa
    0.47
    ไว้
    0.46
    appé
    0.45
     promesse
    0.44
     promise
    0.43
     promesa
    0.43
    EDEFAULT
    0.42
    Activations Density 0.579%

    No Known Activations