Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 3473
    Prev
    Next
    INDEX
    Explanations

    terms related to deportation and legal proceedings concerning immigrants

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

    People who receive something

    np_acts-logits-general · gemini-2.0-flash

    victims and recipients

    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
     Efq
    -0.70
    MethodManager
    -0.67
    TProtocol
    -0.63
    UserScript
    -0.62
     midwives
    -0.62
    scrapy
    -0.62
     editors
    -0.62
     psychiatrists
    -0.60
     Profess
    -0.59
     teachers
    -0.59
    POSITIVE LOGITS
     recipient
    1.50
     recipients
    1.48
     Recipients
    1.20
    recipient
    1.19
     beneficiary
    1.15
    Recipients
    1.15
     Recipient
    1.15
     beneficiaries
    1.14
     victim
    1.13
     victims
    1.11
    Activations Density 0.807%

    No Known Activations