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. 15483
    Prev
    Next
    INDEX
    Explanations

    numbers, dates, or numerical sequences in text

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

    Dates with day of the month

    np_acts-logits-general · gemini-2.0-flash

    dates and specific days

    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
    ])));
    -0.80
    ])))
    -0.69
    EndInit
    -0.67
    '}';
    -0.66
    ))));
    -0.65
     lenker
    -0.65
    ]]
    
    -0.63
    }}$\\
    -0.62
    ]<=
    -0.61
    tagHelperRunner
    -0.61
    POSITIVE LOGITS
    th
    0.94
    kuuta
    0.75
    rd
    0.68
    rungsseite
    0.61
    TagMode
    0.55
    脚注の使い方
    0.55
    ьере
    0.51
    evening
    0.50
     issue
    0.50
    IntoConstraints
    0.48
    Activations Density 0.127%

    No Known Activations