© 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. 18-GEMMASCOPE-RES-16K
    11. 2529
    Prev
    Next
    INDEX
    Explanations

    specific numerical values associated with significant concepts or events

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

    after abbreviations or initialisms

    np_acts-logits-general · gemini-2.0-flash

    cheap commercial content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -1.06
     propOrder
    -1.03
    setVerticalGroup
    -1.00
    tonode
    -0.99
    MemoryWarning
    -0.97
    awtextra
    -0.96
     صوتيه
    -0.96
    DockStyle
    -0.96
     الرياضيه
    -0.95
    ChildScrollView
    -0.94
    POSITIVE LOGITS
     viagra
    0.65
     
    0.64
     https
    0.61
     cheap
    0.56
     cbd
    0.56
    cheap
    0.56
     best
    0.55
     Cheap
    0.54
     The
    0.54
     Best
    0.54
    Activations Density 0.309%

    No Known Activations