© 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. 18-GEMMASCOPE-RES-16K
    11. 1954
    Prev
    Next
    INDEX
    Explanations

    terms related to domestic issues, particularly domestic violence and associated legal matters

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

    "domestic violence" or "domestic"

    np_acts-logits-general · gemini-2.0-flash

    domestic violence or law

    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
     AssemblyCulture
    -0.70
     angeb
    -0.57
    AnimationsModule
    -0.55
     StringTokenizer
    -0.51
     spéciales
    -0.50
    unhofer
    -0.49
     τά
    -0.48
    AccessorTable
    -0.48
    มาะ
    -0.47
    tvguidetime
    -0.47
    POSITIVE LOGITS
     domestic
    1.13
     Domestic
    1.10
    domestic
    1.07
    Domestic
    1.03
    ESTIC
    0.96
     domesti
    0.91
    ally
    0.88
     domestically
    0.81
    SequentialGroup
    0.81
    ALLY
    0.75
    Activations Density 0.036%

    No Known Activations