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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 1513
    Prev
    Next
    INDEX
    Explanations

    text related to academic publications and legal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.51
    ̸
    -0.47
    {
    
    
    -0.43
    setDo
    -0.43
    AnchorTagHelper
    -0.41
     sinto
    -0.41
    vimeo
    -0.40
    ítő
    -0.40
    buttonBar
    -0.40
    ))){
    -0.39
    POSITIVE LOGITS
     revisions
    0.90
     revision
    0.87
     revised
    0.86
     revise
    0.82
     revising
    0.82
     updating
    0.78
     updated
    0.77
    MemoryWarning
    0.76
     edition
    0.74
     Revisions
    0.74
    Activations Density 0.432%

    No Known Activations