© 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. 25-GEMMASCOPE-RES-16K
    11. 10008
    Prev
    Next
    INDEX
    Explanations

    phrases focused on the concept of being "based" or foundational aspects of various arguments or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.68
    RegistryLite
    -0.67
    enderror
    -0.66
    withIdentifier
    -0.64
     oprot
    -0.63
    WithIOException
    -0.63
     مشين
    -0.61
    __);
    -0.59
    TagHelper
    -0.59
     surla
    -0.58
    POSITIVE LOGITS
     primarily
    1.36
     largely
    1.33
     mainly
    1.29
     entirely
    1.26
     mostly
    1.25
     predominantly
    1.17
     chiefly
    1.17
     principally
    1.15
     solely
    1.14
    primarily
    1.06
    Activations Density 0.597%

    No Known Activations