© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 14848
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and contractual obligations

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

    Follows "the," and precedes legal/official terms

    np_acts-logits-general · gemini-2.0-flash

    legal and formal terms

    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
     gyhoeddwyd
    -0.76
     CreateTagHelper
    -0.56
     Luckily
    -0.54
    ::::::::
    -0.54
    TemporalType
    -0.53
     famously
    -0.53
    észetes
    -0.52
     dür
    -0.52
     luckily
    -0.52
     ça
    -0.52
    POSITIVE LOGITS
     foregoing
    1.00
     above
    0.90
     said
    0.84
     applicable
    0.83
     aforesaid
    0.83
     provisions
    0.81
    above
    0.74
     present
    0.74
     herein
    0.73
     undersigned
    0.70
    Activations Density 0.954%

    No Known Activations