© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14215
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contrast or overcoming challenges

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

    "despite"

    np_acts-logits-general · gemini-2.0-flash

    despite something

    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
     russes
    -0.43
    Русский
    -0.38
     officiers
    -0.38
     coordonnées
    -0.36
    IntegerField
    -0.35
    nivå
    -0.35
     vertes
    -0.35
     lampe
    -0.34
     Leer
    -0.34
     ön
    -0.34
    POSITIVE LOGITS
     despite
    1.14
    despite
    1.12
    ostante
    1.08
     Despite
    1.05
     nonostante
    1.04
    Despite
    1.02
     malgré
    0.94
     trotz
    0.91
     Malgré
    0.88
    Trotz
    0.84
    Activations Density 0.128%

    No Known Activations