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. 15-GEMMASCOPE-RES-16K
    6. 8586
    Prev
    Next
    INDEX
    Explanations

    the presence of specific structural elements or markers in the text, such as tags or identifiers for programming or database schema

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vermögen
    -0.55
     are
    -0.54
     
    -0.53
     in
    -0.53
     no
    -0.52
     T
    -0.52
     to
    -0.52
    verhältnis
    -0.50
    Không
    -0.50
     B
    -0.50
    POSITIVE LOGITS
     estekak
    1.09
    脚注の使い方
    0.99
    >");
    
    0.99
    ArgsConstructor
    0.98
    )");
    
    0.95
    >";
    
    0.94
    '):
    
    0.86
    }")
    
    0.85
     Normdatei
    0.85
     تضيفلها
    0.84
    Activations Density 0.215%

    No Known Activations