Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4-GEMMASCOPE-RES-16K
    6. 3438
    Prev
    Next
    INDEX
    Explanations

    the term "newly" associated with various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Horst
    -0.86
     Horst
    -0.82
    ობ
    -0.70
    ImageContext
    -0.69
     azzurro
    -0.67
     Lourdes
    -0.67
    andExpect
    -0.66
     totem
    -0.66
    цездатний
    -0.65
     الرياضيه
    -0.63
    POSITIVE LOGITS
     newly
    1.55
     Newly
    1.50
    newly
    1.50
    Newly
    1.49
     freshly
    1.03
     finely
    0.96
     nowo
    0.90
    Datuak
    0.89
     recém
    0.81
     beautifully
    0.78
    Activations Density 0.117%

    No Known Activations