© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 16331
    Prev
    Next
    INDEX
    Explanations

    discussions related to crime and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     trusted
    -0.50
     חיצוניים
    -0.48
    wikkeld
    -0.48
     Zelanda
    -0.46
     helplessly
    -0.46
    trusted
    -0.45
    arache
    -0.44
    uppa
    -0.44
     Mühle
    -0.44
     postponement
    -0.43
    POSITIVE LOGITS
     crime
    1.16
     Crime
    1.02
    Crime
    1.02
    crime
    1.00
     CRIME
    0.98
     crimes
    0.95
     Crimes
    0.87
    crimes
    0.84
     crimen
    0.82
     criminal
    0.82
    Activations Density 0.172%

    No Known Activations