© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 37
    Prev
    Next
    INDEX
    Explanations

    references to specific metrics, quantities, or structured data

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

    weeks month Apr glucose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CompleteListener
    -0.41
    adaptiveStyles
    -0.40
    PageFactory
    -0.38
     uska
    -0.36
    SuccessListener
    -0.35
     چنین
    -0.34
     ſame
    -0.34
     '{@
    -0.34
     didst
    -0.34
    bufio
    -0.34
    POSITIVE LOGITS
     AssemblyCompany
    0.49
     nakalista
    0.48
    antası
    0.45
    
    0.42
    AccessorTable
    0.41
    bentar
    0.40
    Anhalt
    0.40
    Ӕ
    0.40
    CodedInputStream
    0.40
     BoxDecoration
    0.39
    Activations Density 0.057%

    No Known Activations