© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 9467
    Prev
    Next
    INDEX
    Explanations

    elements related to numerical data and occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Viele
    -0.56
     everywhere
    -0.56
     muchas
    -0.55
     muchos
    -0.54
    everywhere
    -0.53
     muitas
    -0.52
     многих
    -0.50
    istoitu
    -0.50
     sogget
    -0.50
     many
    -0.50
    POSITIVE LOGITS
    webElementXpaths
    0.83
    分别是
    0.77
     nakalista
    0.73
    AndEndTag
    0.73
     apiece
    0.73
    Kaynakça
    0.72
     including
    0.70
    うちの
    0.70
     respectively
    0.70
    うち
    0.67
    Activations Density 0.788%

    No Known Activations