© 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. 7845
    Prev
    Next
    INDEX
    Explanations

    references to samples and specimen data in research documents

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

    references to "sample" or "samples", particularly in scientific contexts like research methodology and data collection.

    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
     electricidad
    -0.56
     dirigir
    -0.56
    躇
    -0.54
     Byr
    -0.52
     dirección
    -0.49
     urusan
    -0.49
    getFullYear
    -0.48
     directivos
    -0.48
     fonctionnement
    -0.48
    <bos>
    -0.48
    POSITIVE LOGITS
     Sample
    1.26
     sample
    1.21
    Sample
    1.18
     SAMPLE
    1.13
     Samples
    1.11
    sample
    1.10
    SAMPLE
    1.08
     samples
    1.05
    Samples
    1.02
     Sampling
    0.94
    Activations Density 0.096%

    No Known Activations