Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15437
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and variable assignments in programming

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

    SQL queries or code snippets

    np_acts-logits-general · gemini-2.0-flash

    programming variable declarations and data retrieval

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.47
     naquele
    -0.41
     forState
    -0.39
    énario
    -0.38
     econô
    -0.37
     comerciais
    -0.37
     wewnętr
    -0.37
    ieteur
    -0.36
     automatiques
    -0.36
     Extragalactic
    -0.36
    POSITIVE LOGITS
     result
    1.09
     results
    0.94
    result
    0.87
     data
    0.84
     response
    0.84
     насељу
    0.82
     Result
    0.79
    IndentedString
    0.77
    tagHelperRunner
    0.76
     responses
    0.74
    Activations Density 0.162%

    No Known Activations