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. 73445
    Prev
    Next
    INDEX
    Explanations

    discussions related to scientific studies and comparisons in research data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Sub
    -0.41
    きたいと思います
    -0.39
     fich
    -0.39
    Sub
    -0.38
     Fra
    -0.38
    RTLD
    -0.37
     Subsid
    -0.35
    化的
    -0.35
     Gou
    -0.35
     fic
    -0.35
    POSITIVE LOGITS
     ProtoMessage
    0.66
    ValueStyle
    0.58
    twimg
    0.57
    complexContent
    0.56
    AnchorStyles
    0.55
    MemoryWarning
    0.54
    onOptions
    0.54
    AddTagHelper
    0.51
     compared
    0.50
    MigrationBuilder
    0.50
    Activations Density 0.107%

    No Known Activations