© 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. 2738
    Prev
    Next
    INDEX
    Explanations

    discussions about authenticity and depth in political and social contexts

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

    Indicates superficiality, lack of substance, or ideals

    np_acts-logits-general · gemini-2.0-flash

    just not superficial

    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
     CreateTagHelper
    -0.69
     véritables
    -0.66
    DebuggerNonUser
    -0.61
     inesper
    -0.60
    parsedMessage
    -0.60
    bital
    -0.59
     OkHttpClient
    -0.59
    Slf
    -0.56
     originais
    -0.55
     BoxFit
    -0.55
    POSITIVE LOGITS
     superficial
    1.05
     mere
    0.92
     superfic
    0.90
     theoretical
    0.86
     empty
    0.85
     lip
    0.85
     wishful
    0.85
     rhetoric
    0.81
     abstract
    0.81
     merely
    0.81
    Activations Density 0.660%

    No Known Activations