© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4783
    Prev
    Next
    INDEX
    Explanations

    technical terms and variables related to mathematical models and measurements

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

    ending in "e" followed by other characters

    np_acts-logits-general · gemini-2.0-flash

    followed by digits or codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    nya
    -0.63
    kiyor
    -0.62
    intenant
    -0.62
    WriteTagHelper
    -0.56
    cuador
    -0.56
    dshaw
    -0.55
    uskas
    -0.53
    ArgumentParser
    -0.52
    bcryptjs
    -0.51
    spiritual
    -0.50
    POSITIVE LOGITS
    e
    1.12
    ee
    0.81
    eee
    0.81
    ie
    0.78
    eeee
    0.78
    ije
    0.77
    ede
    0.76
    eeeee
    0.74
    ide
    0.73
    ele
    0.73
    Activations Density 1.713%

    No Known Activations