© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14796
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to consent and approval processes in various contexts

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

    Agreement, permission, or consent

    np_acts-logits-general · gemini-2.0-flash

    giving or receiving approval

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    OOTDTY
    -0.54
     تانيه
    -0.48
     Inverse
    -0.46
     slayer
    -0.44
     inverse
    -0.44
    gulama
    -0.44
    أما
    -0.43
    furan
    -0.43
     Normdatei
    -0.43
     boden
    -0.42
    POSITIVE LOGITS
     approval
    2.34
     approve
    1.95
     permission
    1.92
     Approval
    1.90
    approval
    1.85
     approvals
    1.80
     APPROVAL
    1.77
     approved
    1.74
     approves
    1.73
    Approval
    1.69
    Activations Density 0.388%

    No Known Activations