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. 11-GEMMASCOPE-RES-16K
    6. 13110
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "become" and its forms 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 @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nadzieję
    -0.76
     pattes
    -0.72
     žal
    -0.70
     giuri
    -0.69
     '\''
    -0.68
    待って
    -0.67
     Sharks
    -0.66
    rektur
    -0.66
     Langue
    -0.65
     căr
    -0.65
    POSITIVE LOGITS
     become
    1.53
     becoming
    1.49
     became
    1.40
     becomes
    1.35
    become
    1.33
    Become
    1.32
     Becoming
    1.31
     Become
    1.31
    becoming
    1.30
    becomes
    1.29
    Activations Density 0.054%

    No Known Activations