© 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. 11238
    Prev
    Next
    INDEX
    Explanations

    statistics related to household demographics and characteristics

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

    Numbers followed by units of measurement or percentages

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by periods

    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
    principalTable
    -1.09
    mybatisplus
    -1.00
    OGND
    -0.96
    ItemBackground
    -0.96
     Walkover
    -0.96
    richTextPanel
    -0.94
    IUrlHelper
    -0.92
    Personensuche
    -0.90
     Италијани
    -0.90
    
    -0.88
    POSITIVE LOGITS
    .
    0.51
     shared
    0.46
     
    0.44
    ,
    0.41
     flat
    0.39
     one
    0.39
    AGER
    0.38
     Shared
    0.35
    symmetric
    0.35
    []
    0.35
    Activations Density 0.515%

    No Known Activations