© 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. 2583
    Prev
    Next
    INDEX
    Explanations

    terms related to custom installations and types of configurations

    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
    contentPane
    -0.48
    setVerticalGroup
    -0.43
    delwed
    -0.43
    enterOuterAlt
    -0.42
    Chham
    -0.41
     nakalista
    -0.40
     ModelExpression
    -0.40
    withOpacity
    -0.39
    AddTagHelper
    -0.39
    HasAnnotation
    -0.38
    POSITIVE LOGITS
     custom
    3.95
     Custom
    3.59
    custom
    3.52
    Custom
    3.45
     CUSTOM
    3.09
     customized
    3.08
    CUSTOM
    2.94
     customised
    2.83
     customize
    2.77
     Customized
    2.72
    Activations Density 0.535%

    No Known Activations