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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 8500
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal agreements and plea bargains

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

    "In exchange for"

    np_acts-logits-general · gemini-2.0-flash

    in exchange for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icato
    -0.31
     surla
    -0.31
    洒
    -0.30
    csol
    -0.29
    èvement
    -0.29
     Mackie
    -0.28
     пробе
    -0.28
    kym
    -0.27
    libft
    -0.27
    CppMethod
    -0.27
    POSITIVE LOGITS
     exchange
    2.67
     exchanged
    2.30
    exchange
    2.27
    Exchange
    2.16
     exchanging
    2.11
     échange
    2.09
     EXCHANGE
    2.08
     exchanges
    2.02
     Exchange
    2.00
    EXCHANGE
    1.91
    Activations Density 0.521%

    No Known Activations