© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102191
    Prev
    Next
    INDEX
    Explanations

    numerical values and status indicators related to system commands or configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onActivityResult
    -0.55
     تعدى
    -0.50
     doInBackground
    -0.49
    ethene
    -0.49
     disambiguazione
    -0.47
     TreeMap
    -0.46
    IRQn
    -0.46
     Renner
    -0.45
    Viitteet
    -0.45
     Soriano
    -0.45
    POSITIVE LOGITS
    Tikang
    0.39
     AssemblyVersion
    0.38
     voorwaarden
    0.36
    ſelf
    0.34
    保险
    0.33
    География
    0.33
    LookAnd
    0.32
     antidesliz
    0.32
    Då
    0.32
    Étape
    0.32
    Activations Density 0.014%

    No Known Activations