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. 20-GEMMASCOPE-RES-16K
    6. 3161
    Prev
    Next
    INDEX
    Explanations

    references to the word "Ter" and its variations in different contexts

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

    starting with "Ter" or "ter"

    np_acts-logits-general · gemini-2.0-flash

    words starting with ter

    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
    mybatisplus
    -0.75
    Xna
    -0.73
    UserScript
    -0.73
    发表于
    -0.66
    httphttps
    -0.66
     AssemblyCulture
    -0.65
    Zeneca
    -0.65
    ulitis
    -0.64
    sidemargin
    -0.64
    ollectionView
    -0.64
    POSITIVE LOGITS
     Ter
    0.66
     termites
    0.58
    terms
    0.52
     terms
    0.51
     TER
    0.50
    Ter
    0.50
    IsMutable
    0.49
     ter
    0.49
     termite
    0.47
     termini
    0.47
    Activations Density 0.073%

    No Known Activations