© 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. 20-GEMMASCOPE-RES-16K
    11. 11137
    Prev
    Next
    INDEX
    Explanations

    details related to accidents and legal proceedings

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

    Legal or crime-related reports

    np_acts-logits-general · gemini-2.0-flash

    police and investigations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.80
     चीज़ों
    -0.67
     initComponents
    -0.67
    ftagPool
    -0.65
    المشاركات
    -0.65
    AutoScaleMode
    -0.65
     hiszen
    -0.64
    FormTagHelper
    -0.64
     kaarangay
    -0.61
     autorytatywna
    -0.61
    POSITIVE LOGITS
     police
    1.59
     investigators
    1.35
    Police
    1.34
     Police
    1.32
     authorities
    1.26
    police
    1.20
    Authorities
    1.15
    Investigators
    1.14
     POLICE
    1.08
     cops
    1.07
    Activations Density 0.264%

    No Known Activations