Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 1439
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to criminal activities and drug trafficking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setTransform
    -0.44
     prawda
    -0.40
    니까
    -0.39
    maßen
    -0.39
    Conclusie
    -0.39
    ària
    -0.38
    partimento
    -0.38
    erapa
    -0.38
    więcej
    -0.38
     bomberos
    -0.37
    POSITIVE LOGITS
    parsedMessage
    0.90
    ReusableCell
    0.88
    RegressionTest
    0.88
     <<<<<<<<<<<<<<
    0.84
    webElementGuid
    0.78
    PreferredItem
    0.76
    
    0.75
    +#+#
    0.74
     betweenstory
    0.74
    存于互联网档案馆
    0.73
    Activations Density 0.422%

    No Known Activations