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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 40831
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific variables related to biological and computational methodologies

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

    Technical and domain-specific terminology that appears in formal documentation, research papers, or specialized texts across fields like computer science, biology, mathematics, and legal writing.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    曖昧さ回避
    -0.51
     onely
    -0.44
     GenerationType
    -0.41
    webElementXpaths
    -0.39
     Magdalena
    -0.39
     Nicolás
    -0.39
    ൈ
    -0.38
     rendered
    -0.37
     nakalista
    -0.36
    ই
    -0.36
    POSITIVE LOGITS
     HttpNotFound
    0.65
    StructEnd
    0.56
    AccessorTable
    0.55
    Népesség
    0.53
    +#+#
    0.49
     PeEnEo
    0.47
    aarrggbb
    0.44
    DockStyle
    0.43
    -------------</
    0.42
     Roskov
    0.41
    Activations Density 0.102%

    No Known Activations