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. 2-GEMMASCOPE-RES-16K
    6. 3949
    Prev
    Next
    INDEX
    Explanations

    terms related to programming or technical specifications, particularly focusing on code errors and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NEP
    -0.61
    '):
    
    -0.54
     htons
    -0.53
     interesar
    -0.51
    awtextra
    -0.51
    eload
    -0.51
    potranspiration
    -0.49
     Abonnez
    -0.49
    DotNetBar
    -0.49
     Measure
    -0.48
    POSITIVE LOGITS
    ExecutionContext
    0.94
    XmlAccessType
    0.84
    angular
    0.73
    ang
    0.72
     للاسماء
    0.64
    WebElementEntity
    0.64
    StructEnd
    0.62
    TagMode
    0.61
    :✨
    0.61
    ANG
    0.60
    Activations Density 1.855%

    No Known Activations