Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 2920
    Prev
    Next
    INDEX
    Explanations

    programming-related structures and syntax

    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
     ї
    -0.21
    تقاوى
    -0.20
     berühmten
    -0.16
     απ
    -0.16
    RMSE
    -0.16
     ţ
    -0.16
     famously
    -0.15
    -
    -0.15
    CPT
    -0.14
    tagHelper
    -0.14
    POSITIVE LOGITS
    ſicht
    1.03
    ſſung
    1.01
    niſſe
    0.99
     témoig
    0.99
     EconPapers
    0.98
    iſchen
    0.98
    ésultats
    0.96
     zwiſchen
    0.96
    ロウィン
    0.95
     ddelwed
    0.95
    Activations Density 0.472%

    No Known Activations