© 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. 22-GEMMASCOPE-RES-16K
    11. 10697
    Prev
    Next
    INDEX
    Explanations

    technical terms and keywords related to programming, particularly focusing on structures and functions in a coding context

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

    Frees memory in GTK

    np_acts-logits-general · gemini-2.0-flash

    set, free, register, unregister

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    доб
    -0.42
    ↵↵
    -0.42
    ↵
    -0.40
     
    -0.40
     sue
    -0.39
     воспользова
    -0.38
    含有
    -0.37
     reels
    -0.36
    อะ
    -0.36
     covered
    -0.35
    POSITIVE LOGITS
    
    1.03
    ⓧ
    0.96
    Vidite
    0.84
    queryInterface
    0.82
     الحره
    0.81
    WriteAttribute
    0.78
    مراجع
    0.78
    AsUp
    0.78
     елның
    0.78
     hâte
    0.77
    Activations Density 0.457%

    No Known Activations