Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 728
    Prev
    Next
    INDEX
    Explanations

    instances of the greater than symbol (>)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     AssemblyCompany
    -0.93
    脚注の使い方
    -0.83
     فريبيس
    -0.79
    tvguidetime
    -0.77
     pinulongan
    -0.76
    featureID
    -0.73
    ſcher
    -0.73
    ंदीखरीदारी
    -0.72
    ReusableCell
    -0.71
    GraphicsUnit
    -0.71
    POSITIVE LOGITS
    >
    0.69
    )
    0.59
    '>
    0.59
    rangle
    0.57
    )}
    0.55
    ]>
    0.54
    )}>
    0.54
    )]
    0.52
    ()}>
    0.52
    }>
    0.51
    Activations Density 0.016%

    No Known Activations