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. 2-GEMMASCOPE-RES-16K
    6. 4927
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to statutes and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.73
    enterOuterAlt
    -0.69
    jectures
    -0.66
     estekak
    -0.65
    RegistryLite
    -0.65
     BorderRadius
    -0.63
     FetchType
    -0.62
    iedo
    -0.61
    λίου
    -0.60
    AnchorStyles
    -0.59
    POSITIVE LOGITS
    
    0.66
    Composable
    0.58
    :✨
    0.58
    rungsseite
    0.58
    iomanip
    0.53
     دیکھیے
    0.53
    : 
    0.52
     Molière
    0.49
    ompi
    0.49
     podjet
    0.48
    Activations Density 0.240%

    No Known Activations