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. 16-GEMMASCOPE-RES-16K
    6. 6299
    Prev
    Next
    INDEX
    Explanations

    specific coding constructs or structure in programming syntax

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

    Code annotations and imports

    np_acts-logits-general · gemini-2.0-flash

    question answer pairs

    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
    errHandler
    -0.61
    MethodManager
    -0.60
    ValueGeneration
    -0.58
     crews
    -0.55
    ConverterFactory
    -0.54
    dotenv
    -0.53
    UnknownFields
    -0.52
     nvm
    -0.51
     Citations
    -0.49
    újo
    -0.49
    POSITIVE LOGITS
     NgModule
    0.70
    SneakyThrows
    0.63
    SpringBootTest
    0.60
     Paglinawan
    0.57
     recevrez
    0.55
    ,@
    0.53
    anskrit
    0.53
     Injectable
    0.52
     переписи
    0.52
    Composable
    0.51
    Activations Density 0.034%

    No Known Activations