© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10308
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to court rulings and agreements

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

    Follows verbs like conclude, enter, order, or attempt

    np_acts-logits-general · gemini-2.0-flash

    past tense verbs followed by "that"

    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
     pon
    -0.43
     Bey
    -0.42
     emer
    -0.39
     Sp
    -0.38
     cri
    -0.37
     СП
    -0.36
     Perp
    -0.36
     boule
    -0.35
     posti
    -0.35
     views
    -0.35
    POSITIVE LOGITS
     mijne
    0.70
     przecież
    0.60
     zelve
    0.60
     Konzentration
    0.58
     zijne
    0.54
    pecabe
    0.53
     Infór
    0.52
     męska
    0.52
     meeste
    0.51
     desmotivaciones
    0.51
    Activations Density 0.963%

    No Known Activations