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. 16-GEMMASCOPE-RES-16K
    6. 16004
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "new" in various contexts

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

    "new" or "New"

    np_acts-logits-general · gemini-2.0-flash

    introducing something new

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /*
    -0.73
     Assisi
    -0.71
     accompagner
    -0.65
     hindsight
    -0.64
     témo
    -0.64
     goddesses
    -0.63
     humaine
    -0.63
     själva
    -0.63
     MacGregor
    -0.63
     Hepburn
    -0.63
    POSITIVE LOGITS
     New
    1.03
     york
    0.93
     NEW
    0.92
    New
    0.90
    ness
    0.89
    newData
    0.88
    fang
    0.88
     newOwner
    0.86
     new
    0.86
     newData
    0.83
    Activations Density 0.107%

    No Known Activations