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. 7475
    Prev
    Next
    INDEX
    Explanations

    functions and methods in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     hotel
    -0.46
    寝
    -0.44
     vol
    -0.44
     cama
    -0.43
     uova
    -0.42
    DialogFragment
    -0.41
    rotto
    -0.41
     Roth
    -0.41
     vols
    -0.40
     drug
    -0.40
    POSITIVE LOGITS
     parser
    0.96
     syntax
    0.90
    parser
    0.89
     parse
    0.87
     Lexer
    0.87
     parsing
    0.85
     Interpreter
    0.85
     Parser
    0.84
     BNF
    0.81
     compiler
    0.78
    Activations Density 0.732%

    No Known Activations