© 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. 0-GEMMASCOPE-RES-16K
    6. 8983
    Prev
    Next
    INDEX
    Explanations

    repeated mentions or emphasis on the concept of "service."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebElementEntity
    -0.81
     Theſe
    -0.78
     Audiodateien
    -0.76
     ainfi
    -0.75
    jectures
    -0.75
     Monfieur
    -0.74
    MLLoader
    -0.74
     ſind
    -0.72
     sauvages
    -0.72
     doubtnut
    -0.72
    POSITIVE LOGITS
     service
    4.63
     Service
    4.27
    service
    4.00
    Service
    3.99
     SERVICE
    3.76
    SERVICE
    3.48
    ervice
    3.17
     servicio
    3.13
     services
    2.84
     serviço
    2.79
    Activations Density 0.049%

    No Known Activations