© 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. 9252
    Prev
    Next
    INDEX
    Explanations

    words beginning with specific letter combinations or sounds

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

    Two or three letter word beginnings

    np_acts-logits-general · gemini-2.0-flash

    clins, splurges, PlGF, class, names

    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
    ed
    -1.13
    ever
    -0.94
    으로
    -0.91
    able
    -0.90
    ا
    -0.86
    ages
    -0.79
    ians
    -0.79
    age
    -0.76
    i
    -0.75
    a
    -0.75
    POSITIVE LOGITS
    isation
    0.43
    led
    0.42
    lel
    0.42
    lect
    0.41
    ism
    0.41
    isi
    0.39
    lium
    0.39
    isk
    0.39
    om
    0.38
    lec
    0.38
    Activations Density 0.429%

    No Known Activations