© 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. 16-GEMMASCOPE-RES-16K
    11. 4593
    Prev
    Next
    INDEX
    Explanations

    structures related to data handling

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

    Code or data structure syntax

    np_acts-logits-general · gemini-2.0-flash

    lists of items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theſe
    -0.88
    MigrationBuilder
    -0.85
     AssemblyCompany
    -0.85
     Numerade
    -0.78
     ſeveral
    -0.78
     Paglinawan
    -0.77
     itſelf
    -0.74
    SourceChecksum
    -0.72
    LEncoder
    -0.72
    Зноскі
    -0.72
    POSITIVE LOGITS
     including
    0.56
    including
    0.49
     themselves
    0.45
    の中から
    0.42
    воря
    0.41
     incluindo
    0.41
     incluyendo
    0.41
    WICH
    0.40
    かな
    0.39
    Hentet
    0.38
    Activations Density 0.399%

    No Known Activations