© 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. 15190
    Prev
    Next
    INDEX
    Explanations

    references to floating-point data types and associated terminology

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

    Floating-point numbers or related terms

    np_acts-logits-general · gemini-2.0-flash

    float and floating variations

    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
    TagMode
    -0.80
    ]")]
    -0.77
    MLLoader
    -0.66
     onItemClick
    -0.59
    guém
    -0.57
    ритори
    -0.57
    jooq
    -0.56
     NgModule
    -0.56
     eletrônico
    -0.55
     AsyncTask
    -0.55
    POSITIVE LOGITS
     floats
    1.09
     floated
    1.04
     Float
    1.03
     FLOAT
    0.98
     float
    0.98
     Floating
    0.93
    Float
    0.93
    Floating
    0.92
     FLO
    0.88
     flot
    0.88
    Activations Density 0.083%

    No Known Activations