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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 2099
    Prev
    Next
    INDEX
    Explanations

    references to particle filters and related statistical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HasFactory
    -0.94
     متعلقه
    -0.91
    (!__
    -0.90
    
    -0.89
    évaluateur
    -0.81
     Ause
    -0.76
     >=",
    -0.74
     contextLoads
    -0.73
    __':
    
    -0.73
    SpringBootTest
    -0.73
    POSITIVE LOGITS
    P
    0.95
     Pn
    0.92
     Pals
    0.91
     P
    0.90
    PU
    0.87
     Pá
    0.85
     PCS
    0.82
     Pirates
    0.82
     PPA
    0.81
    Pá
    0.81
    Activations Density 5.455%

    No Known Activations