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. 22-GEMMASCOPE-RES-16K
    6. 5729
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the importance of taking matters and responsibilities seriously

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

    "Seriously" or variations after certain words

    np_acts-logits-general · gemini-2.0-flash

    taken seriously

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "..\..\
    -0.61
    RenderAtEndOf
    -0.60
     Wylie
    -0.56
    Portály
    -0.54
     "..\..\..\
    -0.53
    rlpool
    -0.50
    неопр
    -0.49
     &___
    -0.49
    Παραπομπές
    -0.48
    Referanser
    -0.48
    POSITIVE LOGITS
     seriously
    2.05
     serious
    1.80
    seriously
    1.79
     seriousness
    1.69
     Serious
    1.64
     Seriously
    1.64
    Serious
    1.62
    serious
    1.62
     serius
    1.61
    Seriously
    1.46
    Activations Density 0.177%

    No Known Activations