© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4141
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to parenthood and citizenship rights

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

    Born out of wedlock

    np_acts-logits-general · gemini-2.0-flash

    marriage and wedlock

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    visionnement
    -0.55
    רושלים
    -0.50
    Inclusion
    -0.48
    ätigkeit
    -0.47
     Diversion
    -0.46
    ')));
    -0.46
    áneamente
    -0.46
    allerie
    -0.46
    ósz
    -0.45
     émer
    -0.45
    POSITIVE LOGITS
     marriage
    2.42
     married
    2.28
     marry
    2.15
     marriages
    2.08
     marrying
    2.07
     Marriage
    2.01
    marriage
    2.00
    Marriage
    1.94
     marries
    1.91
    married
    1.86
    Activations Density 0.666%

    No Known Activations