© 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. 38558
    Prev
    Next
    INDEX
    Explanations

    phrases that describe state or condition, particularly using forms of the verb "to be"

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

    was just / is often

    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
     disambiguazione
    -0.66
    ///</
    -0.57
    liceerd
    -0.42
    nsito
    -0.42
    CodedInputStream
    -0.42
     kasarigan
    -0.41
    webElementXpaths
    -0.40
    Vidite
    -0.40
     важ
    -0.36
     arşivlendi
    -0.36
    POSITIVE LOGITS
    tableFuture
    0.50
     probably
    0.50
    WriteTagHelper
    0.47
    HomeAsUpEnabled
    0.46
     chyba
    0.45
     BoxFit
    0.44
     pretty
    0.43
     perhaps
    0.43
     secoli
    0.41
     prolly
    0.41
    Activations Density 0.052%

    No Known Activations