Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 8706
    Prev
    Next
    INDEX
    Explanations

    items related to organization and space-saving solutions

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

    storage or placement

    np_acts-logits-general · gemini-2.0-flash

    storage shelves and cabinets

    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
     nonatomic
    -0.62
    EndContext
    -0.61
    FunctionFlags
    -0.61
     Pool
    -0.59
    LLocation
    -0.58
     للاسماء
    -0.57
    Portale
    -0.56
    Pool
    -0.55
     pool
    -0.54
     Pools
    -0.54
    POSITIVE LOGITS
     shelves
    1.22
     shelving
    1.15
     drawers
    1.12
     closet
    1.11
     storage
    1.10
     cabinets
    1.08
     shelf
    1.07
     closets
    1.05
     Shelves
    1.03
     drawer
    1.02
    Activations Density 0.098%

    No Known Activations