© 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. 2925
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and specific formatting in code

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

    "import" in Java or other programming languages

    np_acts-logits-general · gemini-2.0-flash

    import statements in code

    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
    ]--;
    -0.67
    AnchorTagHelper
    -0.59
    bilisi
    -0.54
    Попис
    -0.48
    pet
    -0.48
    idit
    -0.48
    zka
    -0.48
     McKnight
    -0.48
     urbain
    -0.47
    skinned
    -0.47
    POSITIVE LOGITS
    import
    0.93
    Geplaatst
    0.77
    cshtml
    0.72
    Джерела
    0.71
     NgModule
    0.69
    Климат
    0.69
    BeginInit
    0.68
    NewUrlParser
    0.67
    发表于
    0.66
     LoggerFactory
    0.65
    Activations Density 0.014%

    No Known Activations