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. 17-GEMMASCOPE-RES-16K
    6. 5812
    Prev
    Next
    INDEX
    Explanations

    references to Microsoft and related software components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NamedQueries
    -0.67
    Rüyada
    -0.65
    GeneratedValue
    -0.63
    TProtocol
    -0.62
     cre
    -0.62
    uvre
    -0.61
    TintMode
    -0.61
    CodedInputStream
    -0.59
     Infirmary
    -0.58
    Poloha
    -0.58
    POSITIVE LOGITS
    Microsoft
    1.24
     Microsoft
    1.20
     microsoft
    1.03
    microsoft
    0.92
     Redmond
    0.82
     Azure
    0.77
    Azure
    0.75
    //
    0.71
    Germania
    0.70
    Forza
    0.70
    Activations Density 0.083%

    No Known Activations