© 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. 22-GEMMASCOPE-RES-16K
    11. 8088
    Prev
    Next
    INDEX
    Explanations

    references to specific areas or regions in scientific or analytical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "area" followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    area under curve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.74
    --}}
    -0.59
    🏻
    -0.59
    ybė
    -0.57
    🏼
    -0.57
    IndentedString
    -0.57
    zzar
    -0.55
    🏻‍♀️
    -0.55
     HasFactory
    -0.53
     occidentalis
    -0.52
    POSITIVE LOGITS
     rugs
    0.87
     rug
    0.83
     AREA
    0.77
     Rugs
    0.75
     Areas
    0.74
     areas
    0.72
     CreateTagHelper
    0.70
    Areas
    0.69
    areas
    0.69
     AREAS
    0.67
    Activations Density 0.116%

    No Known Activations