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. 25-GEMMASCOPE-RES-16K
    6. 3544
    Prev
    Next
    INDEX
    Explanations

    events connected to anniversaries and celebrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    christmas
    -1.08
    Christmas
    -1.06
     Christmas
    -1.06
     christmas
    -0.96
     CHRISTMAS
    -0.94
    DECEMBER
    -0.90
    NOVEMBER
    -0.88
     DECEMBER
    -0.82
     Xmas
    -0.80
     Weihnachten
    -0.80
    POSITIVE LOGITS
     April
    1.79
    April
    1.69
     APRIL
    1.37
     april
    1.36
    APRIL
    1.36
     Easter
    1.34
    april
    1.31
    Easter
    1.26
     May
    1.24
     avril
    1.24
    Activations Density 0.282%

    No Known Activations