© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 15981
    Prev
    Next
    INDEX
    Explanations

    terms related to accusations and allegations of criminal activity, particularly involving trafficking and illegal operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IContainer
    -0.39
    bilirsiniz
    -0.36
     discul
    -0.35
    spender
    -0.34
     сви
    -0.33
    terno
    -0.32
    Ret
    -0.31
    posições
    -0.30
    ția
    -0.30
     Ret
    -0.30
    POSITIVE LOGITS
     illegal
    1.55
     illicit
    1.37
    illegal
    1.36
     smuggling
    1.35
     Illegal
    1.27
     illegally
    1.27
     trafficking
    1.24
    Illegal
    1.22
     smuggled
    1.20
     contraband
    1.17
    Activations Density 0.549%

    No Known Activations