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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 12432
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    This neuron detects mathematical notation with subscripts, particularly indexing variables and mathematical symbols with numeric or alphabetic subscripts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     QtCore
    -0.65
     chociaż
    -0.61
     objectMapper
    -0.57
    Ведь
    -0.57
     aDecoder
    -0.56
     MatDialog
    -0.56
    gusting
    -0.56
    cplusplus
    -0.56
     TestBed
    -0.56
    notated
    -0.56
    POSITIVE LOGITS
    }}^
    0.78
    }^
    0.73
    )^
    0.72
    }_
    0.70
    })^
    0.68
    )}_
    0.67
    }^\
    0.65
    ))^
    0.64
    }}_
    0.63
    ]^
    0.55
    Activations Density 1.177%

    No Known Activations