Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1729
    Prev
    Next
    INDEX
    Explanations

    instances of tax-related terms and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dumne
    -0.48
    didReceive
    -0.48
     nltk
    -0.40
     mCurrent
    -0.39
     figliu
    -0.39
     nowo
    -0.39
     peur
    -0.38
     decoraciones
    -0.37
     volonté
    -0.37
     orta
    -0.37
    POSITIVE LOGITS
    ValueStyle
    1.30
    AddTagHelper
    1.26
    DockStyle
    1.08
    DoubleQuotes
    1.02
     autorytatywna
    0.96
     незавершена
    0.94
    webElementGuid
    0.94
     pinulongan
    0.93
     Chwiliwch
    0.91
    NameInMap
    0.91
    Activations Density 0.422%

    No Known Activations