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. 8-GEMMASCOPE-RES-16K
    6. 8250
    Prev
    Next
    INDEX
    Explanations

    the beginning of a document or a section, specifically looking for the start token

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.83
    BASEPATH
    -0.63
    CppCodeGen
    -0.62
     Wikimedijinoj
    -0.59
    xtext
    -0.59
     Consiglio
    -0.57
     tartalomajánló
    -0.56
    Portale
    -0.56
     Italijani
    -0.56
     فريبيس
    -0.53
    POSITIVE LOGITS
    ParallelGroup
    1.45
     AssemblyProduct
    1.12
    ")]
    
    0.71
    )");
    
    0.70
    endphp
    0.69
    __':
    
    0.67
     ]
    
    0.67
    IBOutlet
    0.67
    ')
    
    0.65
    ंदीखरीदारी
    0.65
    Activations Density 0.013%

    No Known Activations