© 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. 20-GEMMASCOPE-RES-16K
    11. 1269
    Prev
    Next
    INDEX
    Explanations

    phrases that express legal concepts and considerations regarding evidence and their implications

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

    "any" or similar words

    np_acts-logits-general · gemini-2.0-flash

    any issues or outcomes

    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
    Portail
    -0.58
    ătate
    -0.58
    Datuak
    -0.56
    SupportActionBar
    -0.56
     屋根
    -0.56
    Portale
    -0.56
    WireFormatLite
    -0.55
    ]--;
    -0.55
     defaultstate
    -0.55
    PMailer
    -0.53
    POSITIVE LOGITS
     any
    2.37
     eventuali
    2.21
     possible
    1.79
     potential
    1.79
    Any
    1.77
     cualquier
    1.75
     posibles
    1.71
     Any
    1.70
     quaisquer
    1.66
     évent
    1.65
    Activations Density 0.718%

    No Known Activations