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. 16-GEMMASCOPE-RES-16K
    6. 901
    Prev
    Next
    INDEX
    Explanations

    references to FAQs and support information

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

    Preceding tokens: punctuation or uncommon symbols

    np_acts-logits-general · gemini-2.0-flash

    asking questions or getting answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.52
    ```
    
    -0.48
    الإنجليزية
    -0.48
     nomin
    -0.47
    יצוני
    -0.45
     unbalanced
    -0.45
     Cancelar
    -0.45
    зя
    -0.42
    Dangerous
    -0.42
    ณ์
    -0.41
    POSITIVE LOGITS
     answers
    1.24
     answer
    1.06
     answered
    1.06
     answering
    1.04
    answers
    1.00
    Answers
    0.98
     Answers
    0.96
    answer
    0.93
     Answering
    0.92
     FAQ
    0.91
    Activations Density 0.197%

    No Known Activations