© 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. 18-GEMMASCOPE-RES-16K
    11. 15752
    Prev
    Next
    INDEX
    Explanations

    concepts related to governance and legal processes

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

    followed by conjunctions or prepositions

    np_acts-logits-general · gemini-2.0-flash

    phrases starting with With

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebElementEntity
    -0.65
    tanleria
    -0.63
     betweenstory
    -0.63
    fjspx
    -0.60
    avec
    -0.57
     domés
    -0.57
     varandra
    -0.57
     doméstico
    -0.56
     Consortium
    -0.54
     dengan
    -0.53
    POSITIVE LOGITS
     being
    1.10
    being
    0.83
     attached
    0.78
     underway
    0.77
     added
    0.77
     sendo
    0.73
     looming
    0.72
     BEING
    0.71
     included
    0.71
     thrown
    0.68
    Activations Density 0.494%

    No Known Activations