© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 10049
    Prev
    Next
    INDEX
    Explanations

    instances of verbs and their forms, particularly in relation to existence or occurrence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 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
    TestingModule
    -0.38
     CascadeType
    -0.38
     JADX
    -0.38
     pictureBox
    -0.34
    marvin
    -0.34
     textField
    -0.33
    returning
    -0.33
    rubber
    -0.33
     kv
    -0.31
     goodly
    -0.30
    POSITIVE LOGITS
     poveznice
    0.57
     deemed
    0.56
     wordt
    0.53
     adaptarse
    0.51
     aanwezig
    0.51
    webElementXpaths
    0.51
     caratter
    0.50
     tocó
    0.50
     richtet
    0.49
    tadır
    0.49
    Activations Density 1.201%

    No Known Activations