© 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. 37-GEMMASCOPE-RES-16K
    11. 6757
    Prev
    Next
    INDEX
    Explanations

    statements regarding research objectives and goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.60
    posedge
    -0.51
    queryInterface
    -0.49
     виправивши
    -0.47
    getColumnIndex
    -0.47
    الإنجليزية
    -0.47
    PerformLayout
    -0.46
    quiao
    -0.45
     unknownFields
    -0.45
    outWeight
    -0.44
    POSITIVE LOGITS
     goal
    3.23
     goals
    2.89
    goal
    2.73
     aim
    2.64
     objectives
    2.63
     purpose
    2.53
     Goal
    2.50
    Goal
    2.48
     objective
    2.44
     objetivo
    2.41
    Activations Density 1.271%

    No Known Activations