© 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 EvalsExportsinterp-engineNEWAPI 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. 7716
    Prev
    Next
    INDEX
    Explanations

    references to status, requests, or errors related to web applications

    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
     Ten
    -2.17
     ten
    -2.09
    Ten
    -2.05
     TEN
    -1.80
    ten
    -1.72
    TEN
    -1.56
     Tenth
    -1.55
     tenth
    -1.41
    十
    -1.31
     zehn
    -1.22
    POSITIVE LOGITS
     ***!
    0.45
    WriteTagHelper
    0.44
    
    0.41
    nonatomic
    0.40
     հղումներ
    0.39
     BytesLike
    0.38
     AssemblyCulture
    0.37
     tiguan
    0.35
    titleMargin
    0.34
    Rüyada
    0.34
    Activations Density 1.401%

    No Known Activations