Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6072
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to contracts and agreements

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

    Agreement or contract being signed/entered

    np_acts-logits-general · gemini-2.0-flash

    entering into agreements or contracts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    جمعیت
    -0.52
    Lähteet
    -0.50
    istible
    -0.50
     incomplète
    -0.48
    ofman
    -0.47
    thaf
    -0.47
     mandi
    -0.46
    offsetTop
    -0.46
    ::~
    -0.46
    ذف
    -0.45
    POSITIVE LOGITS
     signed
    1.57
     signing
    1.49
     entered
    1.42
     sign
    1.27
     Signing
    1.26
     Signed
    1.24
     negotiated
    1.23
    signed
    1.22
    Signing
    1.21
     заклю
    1.20
    Activations Density 0.308%

    No Known Activations