© 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. 7641
    Prev
    Next
    INDEX
    Explanations

    issues related to technical malfunctions or errors in programming and system functions

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

    words and phrases indicating that something is not functioning properly or failing to work as intended.

    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
    不需要
    -0.45
    无需
    -0.45
    ๆ
    -0.39
    只不过
    -0.38
    不存在
    -0.35
    Werdegang
    -0.34
    CurrentValue
    -0.34
     encantado
    -0.32
    かは
    -0.32
     iLocal
    -0.32
    POSITIVE LOGITS
     properly
    1.13
     adequately
    1.03
     sufficiently
    0.97
     anymore
    0.94
     Properly
    0.93
    IntoConstraints
    0.92
     nor
    0.90
     adequate
    0.87
     PROPER
    0.82
    tagHelperRunner
    0.82
    Activations Density 0.801%

    No Known Activations