© 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. 22-GEMMASCOPE-RES-16K
    6. 10562
    Prev
    Next
    INDEX
    Explanations

    terms related to automotive performance and market trends

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

    Preceding adjectives related to size and price

    np_acts-logits-general · gemini-2.0-flash

    product category descriptions

    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
    AndEndTag
    -0.94
    NameInMap
    -0.68
     gratuites
    -0.49
    WebpackPlugin
    -0.49
     pôr
    -0.48
    ochim
    -0.48
     istruzioni
    -0.47
    ิลป
    -0.47
    RegistryLite
    -0.46
     natale
    -0.46
    POSITIVE LOGITS
     mid
    0.96
     entry
    0.89
     medium
    0.83
     lightweight
    0.81
     compact
    0.79
     budget
    0.79
     premium
    0.77
    entry
    0.77
     middle
    0.77
     Entry
    0.76
    Activations Density 0.248%

    No Known Activations