© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 37749
    Prev
    Next
    INDEX
    Explanations

    phrases expressing strong emotional reactions or exclamations

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

    confirmation/affirmation words

    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
     Wiktionnaire
    -0.54
    ########.
    -0.49
    tableFuture
    -0.41
     dAtA
    -0.38
    KommentareTeilen
    -0.37
    uzz
    -0.37
     '\\;'
    -0.37
    Abp
    -0.37
    })*/
    -0.36
    athread
    -0.36
    POSITIVE LOGITS
     really
    0.90
    果然
    0.83
    不愧
    0.80
     gerçekten
    0.79
    really
    0.77
     truly
    0.75
     действительно
    0.71
    nyata
    0.71
     realmente
    0.70
     amazing
    0.69
    Activations Density 0.011%

    No Known Activations