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. 10-GEMMASCOPE-RES-16K
    6. 12663
    Prev
    Next
    INDEX
    Explanations

    terms related to programming languages, particularly those associated with parsers and query languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LEncoder
    -0.60
     BoxFit
    -0.51
    setupUi
    -0.49
    __()
    -0.47
    TargetException
    -0.47
    InstrumentedTest
    -0.47
    íncia
    -0.45
    )";
    
    -0.45
    ConverterFactory
    -0.45
     JAXBElement
    -0.44
    POSITIVE LOGITS
    ANTLR
    0.93
     صوتيه
    0.81
     nakalista
    0.75
    localctx
    0.74
     gynhyrchwyd
    0.73
    antlr
    0.73
     utafitiHapana
    0.66
    ophyll
    0.61
    inghouse
    0.59
    ########.
    0.59
    Activations Density 0.186%

    No Known Activations