© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 61382
    Prev
    Next
    INDEX
    Explanations

    phrases related to awards and recognition in a critical context

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

    supposed to be

    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
    '}),
    -0.41
    ])).
    -0.39
    ')).
    -0.31
    </thead>
    -0.31
     EconPapers
    -0.31
     }),
    -0.30
    ')),
    -0.29
    seguida
    -0.29
    ineno
    -0.29
     :</
    -0.29
    POSITIVE LOGITS
     supposedly
    1.66
     supuestamente
    1.59
     supposed
    1.51
     prétend
    1.50
    所谓的
    1.48
    supposed
    1.42
     purported
    1.38
    所谓
    1.35
    所謂
    1.34
     angeb
    1.29
    Activations Density 0.454%

    No Known Activations