© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 7538
    Prev
    Next
    INDEX
    Explanations

    terms related to programming constructs and parsers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     becauſe
    -0.44
     vertu
    -0.39
     Perſ
    -0.39
     потреби
    -0.37
     Chriftian
    -0.36
     iſt
    -0.36
     absorption
    -0.36
     houſe
    -0.36
    availability
    -0.35
    capability
    -0.35
    POSITIVE LOGITS
    localctx
    1.16
    RuleContext
    1.05
    SourceChecksum
    0.83
    ANTLR
    0.73
    󠁴
    0.72
    enterOuterAlt
    0.69
    exitRule
    0.65
    errHandler
    0.62
     Autorizaciones
    0.60
     EconPapers
    0.59
    Activations Density 0.080%

    No Known Activations