© 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. 2-GEMMASCOPE-RES-16K
    11. 5291
    Prev
    Next
    INDEX
    Explanations

    nested or hierarchical structures in data, indicated by parentheses and brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.90
     betweenstory
    -0.88
    Personensuche
    -0.83
    ädie
    -0.82
     mergeFrom
    -0.79
     kasarigan
    -0.78
    ✨:
    -0.78
    XMLSchema
    -0.74
    EndProject
    -0.74
     referenties
    -0.74
    POSITIVE LOGITS
    )(((
    0.50
    期刊论文
    0.48
     less
    0.48
     (
    0.45
    (((
    0.44
     any
    0.43
    TagHelpers
    0.43
     Lap
    0.43
     it
    0.40
     access
    0.40
    Activations Density 0.266%

    No Known Activations