© 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. 13250
    Prev
    Next
    INDEX
    Explanations

    key terms related to recalls and actions taken by companies regarding product safety

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

    Comes before citations/references

    np_acts-logits-general · gemini-2.0-flash

    variation regularization

    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
    AN
    -1.46
     AN
    -1.34
    ans
    -1.29
     An
    -1.27
    An
    -1.22
    ANS
    -1.22
    an
    -1.21
    ANT
    -1.21
    ANN
    -1.17
    ann
    -1.12
    POSITIVE LOGITS
    րջ
    0.46
     Kund
    0.45
    "]();
    0.40
    院
    0.40
     Sphere
    0.39
    labus
    0.39
    ابن
    0.39
     Ne
    0.38
    orkin
    0.38
    ატ
    0.38
    Activations Density 0.946%

    No Known Activations