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. 18-GEMMASCOPE-RES-16K
    6. 3911
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and acknowledgment in a context of collaboration or assistance

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

    Gratitude or appreciation

    np_acts-logits-general · gemini-2.0-flash

    thanks and positive outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NOPQRST
    -0.54
    readObject
    -0.46
    ulis
    -0.46
    tså
    -0.46
    呗
    -0.44
    క్క
    -0.43
    MemoryWarning
    -0.42
    UTES
    -0.42
    ylase
    -0.41
    itoral
    -0.41
    POSITIVE LOGITS
     thanks
    2.63
    thanks
    2.25
     gracias
    2.17
     grazie
    2.06
     Thanks
    2.05
     grâce
    2.03
     graças
    2.03
    Thanks
    2.00
     THANKS
    1.83
     dzięki
    1.82
    Activations Density 0.420%

    No Known Activations