© 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. 790
    Prev
    Next
    INDEX
    Explanations

    mandatory or necessary conditions in legal contexts

    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
    ộn
    -0.57
    perror
    -0.55
     Renoir
    -0.55
    adaptiveStyles
    -0.54
     communis
    -0.53
    openzeppelin
    -0.51
    Him
    -0.51
    IsOpen
    -0.50
     '@/
    -0.50
     tabs
    -0.50
    POSITIVE LOGITS
    AddTagHelper
    0.81
    hould
    0.70
     ***!
    0.69
     trebui
    0.67
    SourceChecksum
    0.66
     should
    0.65
    protoimpl
    0.64
     moeten
    0.63
     moet
    0.63
    要在
    0.62
    Activations Density 0.092%

    No Known Activations