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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 6047
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "Des" or related terms within a structured context, possibly indicating a specific subject or category

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     amazing
    -0.77
     Amazing
    -0.73
    amazing
    -0.69
     estekak
    -0.66
    Autoritní
    -0.64
    Amazing
    -0.64
    ]]]
    -0.64
    îné
    -0.63
    تفصیلات
    -0.62
     ChromeDriver
    -0.61
    POSITIVE LOGITS
     Des
    2.35
    Des
    2.29
    des
    2.00
     DES
    1.80
    DES
    1.78
     des
    1.21
     Desh
    1.21
     DESC
    1.03
    Desc
    1.02
     Desc
    1.01
    Activations Density 0.082%

    No Known Activations