© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 16000
    Prev
    Next
    INDEX
    Explanations

    references to services in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -1.23
     Efq
    -1.19
     doubtnut
    -1.19
     himſelf
    -1.16
     Monfieur
    -1.11
     myſelf
    -1.11
     poffe
    -1.08
     fhort
    -1.07
     Majefty
    -1.06
     themſelves
    -1.00
    POSITIVE LOGITS
     service
    1.61
     Service
    1.48
     services
    1.42
    Service
    1.35
     Services
    1.26
    service
    1.20
     SERVICE
    1.19
    SERVICE
    1.16
     Serv
    1.16
    Services
    1.09
    Activations Density 0.031%

    No Known Activations