© 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. 16-GEMMASCOPE-RES-16K
    11. 5488
    Prev
    Next
    INDEX
    Explanations

    terms related to affirmative action and diversity in education or job applications

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

    before commas

    np_acts-logits-general · gemini-2.0-flash

    political/legal issues and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -1.00
     AssemblyTitle
    -0.73
     fometimes
    -0.71
     الرياضيه
    -0.71
    \%)
    -0.69
     \%)
    -0.69
     Jefus
    -0.69
    =""></
    -0.69
     $_"
    -0.67
    )"),
    -0.67
    POSITIVE LOGITS
     debacle
    0.61
     issue
    0.53
     kapcs
    0.50
    问题的
    0.49
     fiasco
    0.49
    件
    0.49
     قض
    0.49
    問題
    0.46
     questione
    0.46
     matters
    0.45
    Activations Density 0.468%

    No Known Activations