© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 7252
    Prev
    Next
    INDEX
    Explanations

    mathematical notations, particularly relating to functions, indices, and subscripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ”)
    -0.50
    ParseException
    -0.50
    ))
    -0.50
    )')
    -0.50
    )
    -0.48
     ')
    -0.48
    ])
    -0.46
     Faul
    -0.46
     simula
    -0.46
    URLException
    -0.46
    POSITIVE LOGITS
    _{
    1.30
    }_{
    1.00
     _{
    0.98
    _{\
    0.93
    <sub>
    0.91
    _{(
    0.85
     }_{
    0.84
     $_{
    0.84
    ]_{
    0.82
    )_{
    0.78
    Activations Density 0.575%

    No Known Activations