© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 14229
    Prev
    Next
    INDEX
    Explanations

    terms related to software licensing and distribution

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

    software distributed under license

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]=>
    -0.33
    ThroughAttribute
    -0.33
    Original
    -0.31
    
    -0.31
     inf
    -0.29
     Meksiku
    -0.29
     بی
    -0.28
    عرِّف
    -0.28
    apnews
    -0.28
    {@
    -0.28
    POSITIVE LOGITS
     software
    1.00
    software
    0.94
    oftware
    0.78
    Software
    0.75
     logiciels
    0.75
     Software
    0.74
    ソフトウェア
    0.71
     softwares
    0.70
     yazılı
    0.68
    WriteTagHelper
    0.66
    Activations Density 0.006%

    No Known Activations