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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53318
    Prev
    Next
    INDEX
    Explanations

    phrases that describe the safety and efficacy concerns of medical treatments

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

    options or alternatives

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    PreferredItem
    -0.88
    adpleegd
    -0.87
    +#+#
    -0.86
     مشين
    -0.86
    
    -0.74
    ༘
    -0.73
     autorytatywna
    -0.73
     ThemeData
    -0.71
    NewUrlParser
    -0.69
    DockStyle
    -0.67
    POSITIVE LOGITS
     or
    1.85
     hoặc
    1.45
     или
    1.38
     atau
    1.36
    或
    1.30
    或者
    1.30
     eller
    1.26
     oder
    1.20
    或者是
    1.20
     或
    1.18
    Activations Density 0.379%

    No Known Activations