© 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. 6292
    Prev
    Next
    INDEX
    Explanations

    important concepts and classifications related to various topics

    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
     frågor
    -0.69
    DispatchToProps
    -0.65
     conjectures
    -0.60
    BeginInit
    -0.59
    ChildScrollView
    -0.59
    itteet
    -0.59
     eksemp
    -0.59
    Gründe
    -0.58
     formulas
    -0.58
     definitions
    -0.57
    POSITIVE LOGITS
     feature
    1.09
     requirement
    1.04
     issue
    1.03
     aspect
    1.03
     trait
    0.97
     idea
    0.96
     option
    0.93
     phenomenon
    0.90
     tactic
    0.87
     suggestion
    0.86
    Activations Density 2.308%

    No Known Activations