© 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. 16-GEMMASCOPE-RES-16K
    11. 1281
    Prev
    Next
    INDEX
    Explanations

    references to coding elements related to database queries and API requests

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

    Code-related punctuation and symbols

    np_acts-logits-general · gemini-2.0-flash

    code syntax and data identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     newArr
    -0.47
     aéreo
    -0.47
     webView
    -0.44
     httpClient
    -0.43
     IOError
    -0.43
    皆
    -0.42
     UIImage
    -0.42
    PostId
    -0.41
    Cited
    -0.40
     whiteColor
    -0.40
    POSITIVE LOGITS
     CreateTagHelper
    0.87
    Personendaten
    0.87
    Autoritní
    0.85
    GEBURTSDATUM
    0.84
    NameInMap
    0.80
    /**
    0.78
    featureID
    0.77
    aarrggbb
    0.77
    enumii
    0.76
    ArgumentParser
    0.76
    Activations Density 0.440%

    No Known Activations