© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4060
    Prev
    Next
    INDEX
    Explanations

    references to chemical compounds or biological terms involving galactose and related derivatives

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

    Suffixes: al, ral, gal, tal, nal, lysis

    np_acts-logits-general · gemini-2.0-flash

    words ending in tal, ral, gal, nal, jal, mal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    으로
    -0.60
    ResponseWriter
    -0.55
    WriteTagHelper
    -0.54
    ally
    -0.54
     convertView
    -0.51
    less
    -0.51
    enterOuterAlt
    -0.50
    alised
    -0.49
    utives
    -0.49
     lupa
    -0.49
    POSITIVE LOGITS
    led
    0.86
    lions
    0.67
    lable
    0.67
    li
    0.67
    lion
    0.66
    lah
    0.65
    lel
    0.63
    la
    0.62
    los
    0.61
    lium
    0.61
    Activations Density 0.249%

    No Known Activations