© 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. 7352
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and structures, particularly those related to arrays and output operations

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

    C++ and Java code syntax and structure elements.

    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
    mittedly
    -0.46
     للاسماء
    -0.39
    moveToFirst
    -0.38
    Aside
    -0.38
    <?
    
    -0.36
     XNUMX
    -0.35
    statuses
    -0.34
    헌
    -0.34
    <!--[
    -0.34
    BigDecimal
    -0.34
    POSITIVE LOGITS
     upto
    0.70
    Govt
    0.68
     wastage
    0.68
     Govt
    0.67
    ⟬
    0.66
     irrespective
    0.65
    govt
    0.63
     govt
    0.63
     lakhs
    0.62
     Diwali
    0.61
    Activations Density 0.088%

    No Known Activations