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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7422
    Prev
    Next
    INDEX
    Explanations

    references to historical and cultural landmarks or sites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.65
     Keuangan
    -0.50
     oscuridad
    -0.43
     cejas
    -0.38
     ResponseEntity
    -0.37
    complexContent
    -0.37
    BeginInit
    -0.35
    CompilerServices
    -0.35
     carreteras
    -0.35
     conejo
    -0.35
    POSITIVE LOGITS
     beach
    0.97
     beachfront
    0.88
     Beach
    0.85
    beach
    0.84
    Beach
    0.82
     coastal
    0.79
     seaside
    0.79
     beaches
    0.78
     BEACH
    0.78
     Coastal
    0.76
    Activations Density 0.412%

    No Known Activations