© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 21832
    Prev
    Next
    INDEX
    Explanations

    numerical data and references related to biological or medical topics

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

    closing parenthesis or asterisk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſicht
    -0.52
    Biographie
    -0.52
    Abitanti
    -0.50
     setOpen
    -0.48
    〮
    -0.48
    streng
    -0.47
     onBind
    -0.47
    koin
    -0.47
    \{\\
    -0.47
     Totals
    -0.47
    POSITIVE LOGITS
    )
    1.05
    )]
    1.02
    ])
    1.02
    ”)
    1.01
    ))
    1.01
    )
    1.00
    )),
    0.97
    ),
    0.97
     )
    0.96
    ]),
    0.95
    Activations Density 1.593%

    No Known Activations