© 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. 11-GEMMASCOPE-RES-16K
    11. 13556
    Prev
    Next
    INDEX
    Explanations

    various forms of user interactions and guidance related to settings or configuration changes within applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     raiſ
    -0.75
     itſelf
    -0.72
     ſever
    -0.71
     Efq
    -0.70
     themſelves
    -0.70
     Majefty
    -0.69
     pleaſure
    -0.67
     ſind
    -0.67
     Anſ
    -0.66
     viſ
    -0.66
    POSITIVE LOGITS
    LookAnd
    0.55
    saraba
    0.54
    StoryboardSegue
    0.52
    の中から
    0.50
    mazaki
    0.49
     RouterModule
    0.48
    kadang
    0.46
    IUrlHelper
    0.44
     кӀ
    0.43
    밍
    0.43
    Activations Density 0.496%

    No Known Activations