© 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. 20-GEMMASCOPE-RES-16K
    11. 881
    Prev
    Next
    INDEX
    Explanations

    quantitative and comparative data in scientific or technical contexts

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

    scientific notation and technical mathematical symbols or references.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    The neuron detects mathematical or citation notation in academic and scientific text, particularly parentheses, superscripts, and specialized reference formatting.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    
    -0.60
     cherchés
    -0.54
    Ӕ
    -0.53
    RegressionTest
    -0.52
    ACHUSET
    -0.51
     становника
    -0.50
    UnknownFieldSet
    -0.49
    tagHelperRunner
    -0.49
    endregion
    -0.49
     detailsLots
    -0.48
    POSITIVE LOGITS
     nôtre
    0.49
    ">)</
    0.47
    >)</
    0.44
     fallu
    0.42
     esclavos
    0.42
     válvulas
    0.42
     infeliz
    0.41
     diarios
    0.41
     casar
    0.40
     CreateTagHelper
    0.39
    Activations Density 1.303%

    No Known Activations