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. 6-GEMMASCOPE-RES-16K
    6. 6256
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'U' and numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -0.92
    ']],
    -0.82
    发表于
    -0.80
     seclu
    -0.79
    }}},
    -0.76
    ())),
    -0.76
     tartalomajánló
    -0.76
    )')
    -0.75
    }}],
    -0.74
    )");
    
    -0.74
    POSITIVE LOGITS
     CURIAM
    0.76
     UIKit
    0.66
    endphp
    0.63
    IgnoreCase
    0.55
    Referències
    0.55
    👍🏻
    0.54
    iastes
    0.52
     UnityEditor
    0.52
     Wikispecies
    0.50
     UnityEngine
    0.50
    Activations Density 0.141%

    No Known Activations