© 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. 39-GEMMASCOPE-RES-16K
    11. 5063
    Prev
    Next
    INDEX
    Explanations

    structured data formats, particularly JSON

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     հղումներ
    -0.74
    PreInfinity
    -0.73
     насељу
    -0.71
     CreateTagHelper
    -0.68
    webElementXpaths
    -0.68
    enterOuterAlt
    -0.67
     resourceCulture
    -0.66
    ineno
    -0.66
     виправивши
    -0.64
     ExecuteAsync
    -0.64
    POSITIVE LOGITS
     igualdad
    0.32
        
    0.26
     Gerechtigkeit
    0.25
     Frühling
    0.24
     Geset
    0.24
     lepas
    0.24
     Gesetze
    0.23
     sunrise
    0.22
     conosci
    0.22
    ตน
    0.21
    Activations Density 0.316%

    No Known Activations