© 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. 8-GEMMASCOPE-RES-16K
    6. 2228
    Prev
    Next
    INDEX
    Explanations

    terms related to real estate and architecture

    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
     HasFactory
    -0.80
     argint
    -0.79
    WarningLevel
    -0.77
    vism
    -0.76
    assium
    -0.73
     Bial
    -0.71
     nivelul
    -0.71
     boar
    -0.71
    UnitTesting
    -0.71
     Pseud
    -0.70
    POSITIVE LOGITS
     furniture
    1.04
     Furniture
    0.93
     furnishings
    0.87
    Furniture
    0.85
     INTERIOR
    0.79
     FURNITURE
    0.78
     Interior
    0.74
    furniture
    0.74
    Decorator
    0.73
     Furn
    0.72
    Activations Density 0.098%

    No Known Activations