© 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. 25-GEMMASCOPE-RES-16K
    11. 8852
    Prev
    Next
    INDEX
    Explanations

    references to specific terms or phrases related to location, especially those that include a "Bur" pattern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    es
    -0.70
    ագրություններ
    -0.61
    complexType
    -0.58
    saraba
    -0.58
    脚注の使い方
    -0.57
    ArrowToggle
    -0.56
    ngdoc
    -0.54
    تقاوى
    -0.53
     ویکی‌پدیای
    -0.51
    esss
    -0.48
    POSITIVE LOGITS
    rrr
    0.62
    rrrr
    0.62
    r
    0.61
    hobo
    0.60
    rrrrrrrr
    0.59
    IBarButtonItem
    0.59
    rer
    0.52
    rr
    0.51
    series
    0.51
    rrrrrr
    0.51
    Activations Density 0.214%

    No Known Activations