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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 24-GEMMASCOPE-RES-16K
    6. 12793
    Prev
    Next
    INDEX
    Explanations

    expressions of personal beliefs and thoughts

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

    "I think" or "I'm" statements

    np_acts-logits-general · gemini-2.0-flash

    I think

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     apparently
    -1.11
    apparently
    -1.07
     supposedly
    -1.06
     Apparently
    -1.05
     seemingly
    -1.02
     allegedly
    -1.02
    Apparently
    -1.01
     reportedly
    -0.97
     supuestamente
    -0.95
     schein
    -0.88
    POSITIVE LOGITS
     propOrder
    0.78
     overall
    0.77
     flesta
    0.76
     ExecuteAsync
    0.74
     meeste
    0.72
    overall
    0.72
    पया
    0.67
    Overall
    0.66
     eher
    0.65
     underrated
    0.65
    Activations Density 0.190%

    No Known Activations