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. 20-GEMMASCOPE-RES-16K
    6. 11588
    Prev
    Next
    INDEX
    Explanations

    references to conferences or events related to academic or professional gatherings

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

    Followed by months or prepositions

    np_acts-logits-general · gemini-2.0-flash

    event dates and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     others
    -0.51
     habit
    -0.45
    Others
    -0.45
    oblo
    -0.43
     pregnancies
    -0.43
    iola
    -0.43
    Vea
    -0.43
    semantics
    -0.42
     dál
    -0.42
    lė
    -0.42
    POSITIVE LOGITS
     estekak
    0.86
    
    0.84
    ########.
    0.83
     held
    0.82
     Held
    0.79
    Held
    0.76
    ьаж
    0.73
     hosted
    0.73
     للمعارف
    0.72
     delegates
    0.71
    Activations Density 0.106%

    No Known Activations