© 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. 4012
    Prev
    Next
    INDEX
    Explanations

    references to data privacy and information security concerning third parties

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

    "third party"

    np_acts-logits-general · gemini-2.0-flash

    third party

    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
    AddTagHelper
    -0.72
    FormTagHelper
    -0.72
    MessageOf
    -0.67
    Hauptartikel
    -0.58
    mockMvc
    -0.55
    BASEPATH
    -0.55
    PhysRevD
    -0.54
    XmlAccessType
    -0.53
    يميديا
    -0.51
     nahilalakip
    -0.50
    POSITIVE LOGITS
     third
    2.68
    third
    2.37
    Third
    2.31
     Third
    2.20
     THIRD
    2.10
    THIRD
    1.99
    第三
    1.81
    第三方
    1.77
     Thirdly
    1.75
     terceros
    1.68
    Activations Density 0.365%

    No Known Activations