© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 14026
    Prev
    Next
    INDEX
    Explanations

    references to programming code and libraries

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

    Code snippets or code-related terms

    np_acts-logits-general · gemini-2.0-flash

    biological activity and code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſei
    -1.75
     queſta
    -1.70
     ſind
    -1.70
    ſehen
    -1.66
    ſicht
    -1.65
    niſſe
    -1.63
    iſchen
    -1.62
     témoig
    -1.61
    ésultats
    -1.59
     $_(
    -1.59
    POSITIVE LOGITS
      
    0.99
    ↵
    0.96
    ↵↵
    0.93
    .
    0.80
       
    0.80
    (
    0.79
    1
    0.77
    <eos>
    0.77
        
    0.76
     ,
    0.75
    Activations Density 37.635%

    No Known Activations