Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 2885
    Prev
    Next
    INDEX
    Explanations

    instances of the word "serious" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.88
    LookAnd
    -0.86
    vismo
    -0.80
     uncin
    -0.78
    ⟬
    -0.78
    Arche
    -0.77
     sindic
    -0.76
    
    -0.75
    RegistryLite
    -0.75
     Wend
    -0.74
    POSITIVE LOGITS
     Serious
    1.37
     serious
    1.31
    Serious
    1.29
    serious
    1.20
     serio
    1.13
     seriously
    1.11
     serius
    1.06
     sérieux
    1.03
     sério
    0.97
     srs
    0.96
    Activations Density 0.055%

    No Known Activations