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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10984
    Prev
    Next
    INDEX
    Explanations

    function declarations and their respective parameters in programming code

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

    Code initialization or constructors

    np_acts-logits-general · gemini-2.0-flash

    initialization and setup methods

    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
     handleChange
    -0.43
     CommandType
    -0.42
    SqlClient
    -0.42
    handleChange
    -0.41
    grep
    -0.41
    RemoveAt
    -0.40
    Modificar
    -0.38
    Restrict
    -0.37
     traded
    -0.37
    ctile
    -0.37
    POSITIVE LOGITS
     initialization
    1.96
     initialize
    1.92
     init
    1.87
    init
    1.76
    初始化
    1.72
     Initialize
    1.72
     Initialization
    1.69
    Initialize
    1.68
     Init
    1.68
     initializing
    1.68
    Activations Density 0.374%

    No Known Activations