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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 7665
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "protocol."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -1.05
     Theſe
    -0.88
     becauſe
    -0.82
     Jefus
    -0.79
     Lire
    -0.78
     Sight
    -0.76
     imageNamed
    -0.76
     ſmall
    -0.74
     Monfieur
    -0.74
     renunciation
    -0.74
    POSITIVE LOGITS
     protocol
    2.10
     protocols
    2.06
     Protocol
    1.94
     Protocols
    1.76
     PROTOCOL
    1.76
    protocol
    1.76
    Protocol
    1.75
    Protocols
    1.53
     protocolo
    1.50
    protocols
    1.48
    Activations Density 0.071%

    No Known Activations