© 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 - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 12169
    Prev
    Next
    INDEX
    Explanations

    phrases related to mistakes and errors

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

    mistakes, errors, or failures in systems and processes.

    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
    protoimpl
    -0.39
    Weblinks
    -0.31
    +:+
    -0.30
     Савезне
    -0.30
     menac
    -0.29
    setVerticalGroup
    -0.29
     hien
    -0.27
     mera
    -0.27
    inqui
    -0.27
    odils
    -0.26
    POSITIVE LOGITS
     mistakes
    2.16
     mistake
    1.88
     Mistakes
    1.84
     errors
    1.76
     blunder
    1.69
     erreurs
    1.63
     errores
    1.59
     error
    1.53
     Mistake
    1.51
     Errors
    1.50
    Activations Density 0.706%

    No Known Activations