© 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. 22-GEMMASCOPE-RES-16K
    11. 10186
    Prev
    Next
    INDEX
    Explanations

    terms related to auditing and regulatory quality improvements

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

    followed by benefits or needs, like "ensure [benefit]"

    np_acts-logits-general · gemini-2.0-flash

    ensure credibility and integrity

    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
     svolta
    -0.54
    ̍
    -0.50
    Verdict
    -0.50
     luckily
    -0.48
     gigantes
    -0.47
     Luckily
    -0.46
     complejos
    -0.46
     ceramica
    -0.44
    棘
    -0.44
    destroyAll
    -0.43
    POSITIVE LOGITS
     transparency
    1.16
     continuity
    1.00
     fairness
    0.99
     consistency
    0.94
     accountability
    0.93
     fair
    0.91
     predictability
    0.87
    consistency
    0.83
     compliance
    0.83
     uniformity
    0.82
    Activations Density 0.500%

    No Known Activations