© 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. 20-GEMMASCOPE-RES-16K
    11. 8068
    Prev
    Next
    INDEX
    Explanations

    coding-related terminology, particularly involving memory allocation and data structure manipulations

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

    C code related to memory size

    np_acts-logits-general · gemini-2.0-flash

    sizeof, offsetof, memory size

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    ู้
    -0.43
     pan
    -0.42
    ionista
    -0.42
    号
    -0.41
    karta
    -0.41
    isfile
    -0.40
    Chham
    -0.40
    בור
    -0.40
    pons
    -0.40
    nasse
    -0.40
    POSITIVE LOGITS
     sizeof
    1.80
    sizeof
    1.77
    offsetof
    0.83
    ReusableCell
    0.81
    SIZ
    0.73
     neceff
    0.65
     purpoſe
    0.64
    Ukuran
    0.64
    providedIn
    0.63
     disambiguazione
    0.62
    Activations Density 0.202%

    No Known Activations