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. 20-GEMMASCOPE-RES-16K
    6. 3488
    Prev
    Next
    INDEX
    Explanations

    programming commands and functions related to credential management

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

    Lines starting with "with self.command_group"

    np_acts-logits-general · gemini-2.0-flash

    `with self` code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
      
    -0.63
    ListOf
    -0.53
     میتوان
    -0.52
    	
    -0.51
     AttributeSet
    -0.50
       
    -0.50
     timeStamp
    -0.49
    cambrian
    -0.49
    setupUi
    -0.47
     ,
    -0.47
    POSITIVE LOGITS
    rungsseite
    0.87
    存于互联网档案馆
    0.65
    ]";
    0.64
     (
    
    0.64
    StoryboardSegue
    0.62
    "],
    
    0.62
    \"]
    0.59
    _${
    0.58
    出版年
    0.58
    =?";
    0.58
    Activations Density 0.186%

    No Known Activations