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. 24-GEMMASCOPE-RES-16K
    6. 14086
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual or entity related to legal or medical issues

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

    "La", followed by capitalized word

    np_acts-logits-general · gemini-2.0-flash

    La followed by names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.56
    Gemeinden
    -0.56
    /*---
    -0.55
    InitVars
    -0.54
     Administrativna
    -0.51
     ComVisible
    -0.51
     Abstracts
    -0.51
     незавершена
    -0.51
     vulgares
    -0.50
    initComponents
    -0.49
    POSITIVE LOGITS
    atste
    0.48
     Grange
    0.46
     StringTokenizer
    0.45
    eti
    0.44
    urier
    0.43
     Defense
    0.42
     Verne
    0.42
    urale
    0.42
    ertes
    0.41
    ird
    0.41
    Activations Density 0.048%

    No Known Activations