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. 17-GEMMASCOPE-RES-16K
    6. 5930
    Prev
    Next
    INDEX
    Explanations

    path and file reference information within system assemblies and programming environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -1.16
     الرياضيه
    -1.15
     AssemblyCulture
    -1.12
    Parcelize
    -1.11
     doubtnut
    -1.10
    setupUi
    -1.07
    DeleteBehavior
    -1.05
     itſelf
    -1.04
    homonymie
    -1.03
    SharedDtor
    -1.00
    POSITIVE LOGITS
     …
    0.55
      
    0.54
     d
    0.54
    _
    0.52
     
    0.52
     H
    0.52
     I
    0.52
     Th
    0.51
    …
    0.50
     $
    0.50
    Activations Density 2.226%

    No Known Activations