© 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. 8-GEMMASCOPE-RES-16K
    11. 15201
    Prev
    Next
    INDEX
    Explanations

    references to domain-related concepts and discussions 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 @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     devons
    -0.79
     celta
    -0.72
    icleta
    -0.69
     McClure
    -0.68
    >//
    -0.68
     engagé
    -0.67
     Clegg
    -0.67
    Schutz
    -0.66
     Scud
    -0.65
     tryp
    -0.65
    POSITIVE LOGITS
     domain
    2.00
     Domain
    1.95
     domains
    1.86
    Domain
    1.74
     DOMAIN
    1.73
    domain
    1.72
     Domains
    1.71
    DOMAIN
    1.64
    domains
    1.57
    Domains
    1.52
    Activations Density 0.076%

    No Known Activations