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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73480
    Prev
    Next
    INDEX
    Explanations

    specific technical components and structures related to engineering and mechanical systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     demais
    -0.46
     contextLoads
    -0.44
    Tē
    -0.40
     parseFrom
    -0.40
     loadData
    -0.39
     propOrder
    -0.39
     userDao
    -0.39
     Sti
    -0.38
     Fortun
    -0.37
     estekak
    -0.37
    POSITIVE LOGITS
     otomatig
    0.53
    CppMethod
    0.48
     GenerationType
    0.47
     CreateTagHelper
    0.46
    
    0.44
     gynhyrchwyd
    0.43
    Personendaten
    0.42
    EndContext
    0.42
    CppCodeGen
    0.41
    dengar
    0.40
    Activations Density 0.138%

    No Known Activations