© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 3684
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal growth and transformation

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

    followed by "become" or a variant of it

    np_acts-logits-general · gemini-2.0-flash

    verbs indicating change of state

    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
    håll
    -0.56
    ี้ยง
    -0.54
    withstanding
    -0.52
    อย่างไร
    -0.52
    Personendaten
    -0.51
    Sucesor
    -0.49
     waited
    -0.49
    willReturn
    -0.48
    shutil
    -0.48
     conocía
    -0.47
    POSITIVE LOGITS
     become
    2.25
     becomes
    2.21
     became
    1.98
     becoming
    1.94
    become
    1.89
    becomes
    1.84
     Become
    1.79
     Becomes
    1.77
    Become
    1.66
    becoming
    1.64
    Activations Density 0.991%

    No Known Activations