© 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. 38-GEMMASCOPE-RES-16K
    11. 13068
    Prev
    Next
    INDEX
    Explanations

    words related to different types of filament or fiber materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.44
     سود
    -0.36
    лючение
    -0.36
    fica
    -0.34
     allAfrica
    -0.34
    LEAVE
    -0.34
     dated
    -0.34
    principalColumn
    -0.33
    FFIC
    -0.33
     leave
    -0.33
    POSITIVE LOGITS
    Referanser
    0.60
    AddTagHelper
    0.54
     kaynağından
    0.51
     дописавши
    0.50
    VersionUID
    0.50
    nalités
    0.49
    SourceChecksum
    0.48
    Билгалдахарш
    0.48
    Diwedd
    0.48
     NavController
    0.47
    Activations Density 0.409%

    No Known Activations