© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 8175
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols, particularly those related to variables and sets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MatDialog
    -0.73
     aDecoder
    -0.71
     незавершена
    -0.66
     >=",
    -0.64
     QtCore
    -0.63
     chociaż
    -0.62
    lgari
    -0.62
    latego
    -0.61
    Ведь
    -0.61
    EDEFAULT
    -0.60
    POSITIVE LOGITS
    }}^
    0.78
    }^
    0.72
    )^
    0.68
    })^
    0.65
    }_
    0.65
    }^\
    0.60
    }}_
    0.59
    ))^
    0.57
    )}_
    0.57
    ^
    0.52
    Activations Density 1.167%

    No Known Activations