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. 3560
    Prev
    Next
    INDEX
    Explanations

    references to wildlife

    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
    IconModule
    -0.65
    URLException
    -0.65
    LayoutStyle
    -0.65
    出版年
    -0.64
     Shal
    -0.63
    InjectAttribute
    -0.63
    ymce
    -0.63
    WindowConstants
    -0.63
     }{@
    -0.61
    تقاوى
    -0.60
    POSITIVE LOGITS
     myſelf
    0.89
     Theſe
    0.78
     alike
    0.76
     Jefus
    0.74
     itſelf
    0.74
     Houſe
    0.73
     houſe
    0.72
     ghosts
    0.71
     theſe
    0.70
     themſelves
    0.68
    Activations Density 0.044%

    No Known Activations