© 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. 3723
    Prev
    Next
    INDEX
    Explanations

    terms related to legal offenses and criminal behavior

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

    Follows "commit" or "a" and relates to crime

    np_acts-logits-general · gemini-2.0-flash

    committing crimes or offenses

    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
    Datuak
    -0.71
    VIAF
    -0.57
    发表于
    -0.56
    complexType
    -0.55
    lementation
    -0.54
    mybatisplus
    -0.54
     rhestr
    -0.54
     buta
    -0.53
    SBATCH
    -0.53
    urator
    -0.52
    POSITIVE LOGITS
     crime
    2.02
     crimes
    1.85
     offenses
    1.72
    crime
    1.72
     offense
    1.72
     offence
    1.70
     offences
    1.69
    crimes
    1.57
     Crime
    1.51
     CRIME
    1.44
    Activations Density 0.572%

    No Known Activations