© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3052
    Prev
    Next
    INDEX
    Explanations

    references to the Internet and connectivity-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nachhaltigkeit
    -0.59
    LogFactory
    -0.58
     Nachhal
    -0.58
     zau
    -0.56
     Gom
    -0.53
     gestes
    -0.52
     MonoBehaviour
    -0.52
     dureza
    -0.52
    Gom
    -0.51
    Raw
    -0.51
    POSITIVE LOGITS
     Internet
    1.71
     INTERNET
    1.58
    Internet
    1.57
     internet
    1.48
    internet
    1.42
    INTERNET
    1.34
     ―――――
    1.05
     NET
    0.96
     الإنترنت
    0.96
     Interne
    0.95
    Activations Density 0.037%

    No Known Activations