© 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. 4128
    Prev
    Next
    INDEX
    Explanations

    references to "the" as well as some quantifiers and indicators of importance in a text

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

    "For the" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    for the purpose of

    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
    خصة
    -0.65
    IndentedString
    -0.61
    stateProvider
    -0.56
    DoubleQuotes
    -0.54
    })()
    -0.51
    "")
    -0.50
    もしれない
    -0.50
    BufferException
    -0.49
     initComponents
    -0.49
    --)
    -0.49
    POSITIVE LOGITS
     sake
    1.96
     purposes
    1.96
    purposes
    1.59
     purpose
    1.49
     Purposes
    1.37
    purpose
    1.26
     reasons
    1.20
    Purpose
    1.19
     Purpose
    1.10
    reasons
    1.07
    Activations Density 0.251%

    No Known Activations