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. 77188
    Prev
    Next
    INDEX
    Explanations

    equal signs in code, indicating assignment operations

    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
     queſta
    -0.85
     ſche
    -0.78
     $_"
    -0.76
    tershire
    -0.75
     faſt
    -0.75
     ſch
    -0.74
    ſelf
    -0.72
     Houſe
    -0.71
     verſ
    -0.71
     zuſammen
    -0.70
    POSITIVE LOGITS
    =
    1.23
     =
    1.02
    ']=
    1.00
    ]=
    0.97
    }=
    0.94
    )=
    0.93
    "]=
    0.92
    ]]=
    0.85
    ++]=
    0.84
    )]=
    0.81
    Activations Density 0.013%

    No Known Activations