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. 8-GEMMASCOPE-RES-16K
    6. 8186
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the idea of irrelevance or indifference to circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hawthorn
    -0.54
    dafrika
    -0.52
     delin
    -0.52
     cref
    -0.52
     Hyde
    -0.51
    IGraphics
    -0.51
    จึง
    -0.51
    umuz
    -0.49
    ̈́
    -0.49
    нє
    -0.49
    POSITIVE LOGITS
    regardless
    1.28
     regardless
    1.26
     Regardless
    1.15
    Regardless
    1.09
     irrespective
    1.05
    dientemente
    1.00
     Infórmanos
    0.95
    importe
    0.93
     whether
    0.91
    hichever
    0.89
    Activations Density 0.111%

    No Known Activations