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

    Neuronpedia

    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. 12-GEMMASCOPE-RES-16K
    11. 12004
    Prev
    Next
    INDEX
    Explanations

    terms related to optimization, specifically focused on loss functions and error minimization in machine learning contexts

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

    technical terms related to error metrics and optimization in mathematical or machine learning contexts, particularly "mean square error", "RMS", and "minimize".

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of quantitative optimization objectives and error metrics—i.e., discussions of loss/cost functions and their minimization or maximization in modeling or training contexts

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.95
    expandindo
    -0.75
     autorytatywna
    -0.75
    WithIOException
    -0.73
    tagHelperRunner
    -0.69
     vPvB
    -0.68
     AssemblyCompany
    -0.68
     שוליים
    -0.68
    Cyfarwyddwr
    -0.68
     estekak
    -0.64
    POSITIVE LOGITS
     loss
    0.56
    loss
    0.54
     Loss
    0.50
    Loss
    0.48
     LOSS
    0.42
     objective
    0.41
     objectives
    0.39
     quality
    0.38
    LOSS
    0.37
     losses
    0.36
    Activations Density 1.350%

    No Known Activations