© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 14255
    Prev
    Next
    INDEX
    Explanations

    phrases that list items or concepts in a series

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

    the word "and" used to connect items in a list or series.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.77
    
    -0.67
    Autoritní
    -0.57
    ItemBackground
    -0.57
    といけない
    -0.54
     JpaRepository
    -0.53
    ContentLoaded
    -0.53
    gtest
    -0.52
     برانيه
    -0.49
     disambiguazione
    -0.49
    POSITIVE LOGITS
     etc
    1.20
    etc
    0.95
     finally
    0.93
     lastly
    0.92
     even
    0.85
     persino
    0.82
     sebagainya
    0.81
    Etc
    0.79
    等等
    0.77
     ultimately
    0.77
    Activations Density 0.395%

    No Known Activations