© 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. 11227
    Prev
    Next
    INDEX
    Explanations

    references to individuals involved in criminal activities and legal proceedings

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

    Person being charged/arrested, or admitting to something

    np_acts-logits-general · gemini-2.0-flash

    admitted, pleaded, confessed

    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
    mybatisplus
    -0.80
    TagMode
    -0.71
     архивлан
    -0.60
     viewDidLoad
    -0.58
     cherchés
    -0.57
    ciatore
    -0.56
    Lähteet
    -0.56
     observing
    -0.56
     observation
    -0.53
    !*\
    -0.52
    POSITIVE LOGITS
     admitted
    1.08
     pleaded
    0.98
     confessed
    0.96
     faces
    0.94
     admitting
    0.93
     plead
    0.93
     pled
    0.89
     admit
    0.88
     Admit
    0.83
     denied
    0.80
    Activations Density 0.505%

    No Known Activations