© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13431
    Prev
    Next
    INDEX
    Explanations

    specific edits or changes in document revisions, particularly involving the removal of references

    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
    WebElementEntity
    -0.76
    UnusedPrivate
    -0.58
    
    -0.48
    hoeddwyd
    -0.47
     istore
    -0.45
    @[+][
    -0.45
    Чыганаклар
    -0.45
    Хьажоргаш
    -0.45
     resourceCulture
    -0.44
    enderror
    -0.43
    POSITIVE LOGITS
     Wikipedia
    1.05
     Wiki
    0.90
     wiki
    0.86
     wik
    0.85
    Wikipedia
    0.83
    Wiki
    0.82
     wikipedia
    0.82
    wiki
    0.79
     Wik
    0.79
     Wikiped
    0.77
    Activations Density 0.714%

    No Known Activations