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. 16-GEMMASCOPE-RES-16K
    6. 8467
    Prev
    Next
    INDEX
    Explanations

    phrases that involve asking for opinions or seeking feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Questions or opinions asked of the reader

    np_acts-logits-general · gemini-2.0-flash

    addressing you or your opinion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    greenrobot
    -0.53
    bkz
    -0.51
     것이다
    -0.51
    ± 
    -0.50
    culature
    -0.45
     basah
    -0.45
    зами
    -0.45
    /**
    -0.45
     koska
    -0.43
    来了
    -0.43
    POSITIVE LOGITS
     yours
    0.88
     you
    0.81
     yourselves
    0.78
    你觉得
    0.74
    you
    0.71
     your
    0.71
    your
    0.71
    みな
    0.69
    yours
    0.68
     vosotros
    0.68
    Activations Density 0.186%

    No Known Activations