© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 5276
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and structures, particularly in a coding or scripting context

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

    Boolean assertions (toBeTrue, toBeFalse)

    np_acts-logits-general · gemini-2.0-flash

    boolean assertions

    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
     виправивши
    -0.71
     متعلقه
    -0.58
    AccessorTable
    -0.55
    Portail
    -0.55
    StoryboardSegue
    -0.55
     kasarigan
    -0.54
    
    -0.53
     ModelRenderer
    -0.52
    DOCTYPE
    -0.50
    __["
    -0.49
    POSITIVE LOGITS
     True
    1.45
     true
    1.43
     TRUE
    1.37
    True
    1.29
    TRUE
    1.26
    true
    1.25
     False
    1.22
     false
    1.14
     FALSE
    1.11
    False
    1.08
    Activations Density 0.188%

    No Known Activations