© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 10216
    Prev
    Next
    INDEX
    Explanations

    database query and user input processing elements

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

    dictionary and array access operations using bracket notation in code.

    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
     come
    -0.34
     came
    -0.33
    (&:
    -0.32
     χει
    -0.30
     jed
    -0.30
     llegado
    -0.29
     mil
    -0.28
     didReceive
    -0.28
     llegó
    -0.27
     bo
    -0.27
    POSITIVE LOGITS
     propOrder
    0.94
    ['
    0.79
    $_['
    0.78
    ["
    0.75
    httphttps
    0.68
    __["
    0.65
    principalColumn
    0.64
    NameInMap
    0.64
     Italijanski
    0.64
    ']['
    0.63
    Activations Density 0.227%

    No Known Activations