© 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. 13239
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or entities, particularly those with notable associations or roles

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

    ending in "on," "yon," or "ion"

    np_acts-logits-general · gemini-2.0-flash

    word parts ending in on followed by specific suffixes

    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
    makeConstraints
    -0.74
     EconPapers
    -0.66
    conio
    -0.65
    SizeMode
    -0.64
    stdc
    -0.62
    UnsafeEnabled
    -0.61
    es
    -0.61
    הערות
    -0.59
    TagHelper
    -0.59
    出版年
    -0.58
    POSITIVE LOGITS
    ghua
    0.60
    tu
    0.59
    ghorn
    0.55
    itrile
    0.54
    :^{
    0.54
    gino
    0.52
    ghu
    0.51
    gin
    0.51
    τως
    0.50
    gh
    0.49
    Activations Density 0.241%

    No Known Activations