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. 10-GEMMASCOPE-RES-16K
    6. 15765
    Prev
    Next
    INDEX
    Explanations

    references to historical events and figures related to slavery and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.70
    meisterschaften
    -0.47
     OFDb
    -0.45
     FLAGS
    -0.45
    transQ
    -0.45
    çade
    -0.44
    extAlignment
    -0.42
     Crate
    -0.42
     flags
    -0.42
    omás
    -0.42
    POSITIVE LOGITS
     ModelExpression
    0.77
     AssemblyCulture
    0.74
    AndEndTag
    0.66
    }))
    
    0.66
    
    0.56
    MENAFN
    0.55
     Pingback
    0.55
     '\\;'
    0.55
    ˈ
    0.54
     Administrativna
    0.54
    Activations Density 1.080%

    No Known Activations