© 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. 7-GEMMASCOPE-RES-16K
    11. 15673
    Prev
    Next
    INDEX
    Explanations

    geographic locations and references to places in Michigan

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     setuptools
    -0.49
    ynb
    -0.43
    }],
    -0.42
    ContentLoaded
    -0.41
    }]
    -0.40
    PostConstruct
    -0.38
    ollectionView
    -0.38
    }))
    -0.37
    ']):
    -0.37
     Pursuit
    -0.36
    POSITIVE LOGITS
     Michigan
    1.45
    Michigan
    1.41
     Detroit
    1.37
    Detroit
    1.31
     DETROIT
    1.27
     MICHIGAN
    1.22
    ROIT
    1.10
    detroit
    1.02
     Mich
    0.88
    higan
    0.85
    Activations Density 0.672%

    No Known Activations