© 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. 1725
    Prev
    Next
    INDEX
    Explanations

    function and lambda syntax in code

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

    Parentheses, especially nested

    np_acts-logits-general · gemini-2.0-flash

    empty parentheses arrow function

    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
    RetentionPolicy
    -0.89
     سكانية
    -0.80
    StructEnd
    -0.77
    WriteBarrier
    -0.74
    IsContent
    -0.71
    ScopeManager
    -0.69
     américains
    -0.69
     bogotá
    -0.67
     defStyleAttr
    -0.66
    withstanding
    -0.66
    POSITIVE LOGITS
    ={()
    0.66
    м
    0.56
    пущен
    0.53
     ak
    0.53
     ListTile
    0.52
     fact
    0.52
    ThemeOverlay
    0.51
     «
    0.50
    (()
    0.49
     Samson
    0.49
    Activations Density 0.033%

    No Known Activations